Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Graphics

cs.GR Watch Graphics

Friday 14 August

Graphics · Cross-listed from cs.CV

Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation

Michael R. Martin, Joseph Insley, Victor A. Mateevitsi et al. (+2 more)

Scientific simulations often produce scalar volumes faster than they can be stored, transferred, and loaded, while in situ reduction must use only a limited share of simulation resources. This work encodes scalar fields as anisotropic Gaussian primitives under a fixed budget. The complete primitive set is allocated analytically from local field structure, including position, orientation, and shape, then refined directly against the scalar field without densification, pruning, or count changes. The selected budget determines encoded storage before refinement and, together with the iteration schedule, provides a controllable refinement-time budget. In a controlled benchmark, truncation-aware field evaluation reduces encoding time by up to 51x; 1.4 million Gaussians encode a billion-voxel volume in at most four minutes on one desktop GPU, with reduced-iteration refinement completing in under one minute. Across five datasets spanning 2.1 million to 1.1 billion evaluated voxels, compression-useful configurations achieve 15.0-38.7 dB PSNR at compression ratios from 2.2x to over 40,000x. Pre-encoding structure statistics characterize fields for which one-shot allocation yields limited gains from additional capacity. Because primitives retain scalar attributes rather than baked appearance, a single compact model serves every subsequent visualization state - supporting post-hoc transfer-function, colormap, lighting, and viewpoint changes without re-encoding.
Read the full abstract

All authors Michael R. Martin, Joseph Insley, Victor A. Mateevitsi, Silvio Rizzi, Kwan-Liu Ma

Graphics · Cross-listed from cs.CV

Content Based Video Narration of Gameplay with Vision Language Models

Mathew Varghese

Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration system that produces spoken, esports-style commentary for arbitrary gameplay recordings using a general-purpose vision-language model (VLM) and a text-to-speech back end, with no game-specific instrumentation, no engine telemetry, and no task-specific training. Three mechanisms carry the system. Temporal mosaic packing arranges nine uniformly sampled frames into a single 3x3 image, letting an image-native VLM reason about motion while consuming one image payload per segment instead of nine. Context-conditioned prompting replays the K most recent narrations as assistant-role history, suppressing the repetition that dominates per-segment captioning of static scenes. Duration-conditioned generation and elastic alignment constrain narration length in the prompt, then time-scale or symmetrically pad the synthesized audio so each utterance fills its segment slot exactly, giving frame-accurate muxing without a forced aligner. The implementation supports either cloud TTS or a 6-bit quantized 4B-parameter on-device TTS model on Apple silicon, making the speech stage fully local. We report a qualitative case study on real-time strategy footage, a cost model showing the mosaic reduces per-minute image payloads by 9x, and a candid account of observed failure modes - hallucinated game state, resolution loss from mosaicking, and prosody artifacts from time-scaling. We release the system as a reproducible baseline, with an evaluation protocol for the quantitative study a full version will report.
Read the full abstract

Graphics · Cross-listed from cs.CV

RGBX-Next: Towards Realistic Generative Rendering from G-Buffers

Zheng Zeng, Marco Salvi, Lifan Wu et al. (+9 more)

Diffusion models have achieved impressive results in image, video, and streaming generation. However, compared to traditional 3D rendering, they still lack precise control over the generated output. We believe a viable path forward is to use generative models as learned renderers conditioned on traditionally rendered G-buffers. We introduce RGBX-Next, a unified generative framework for forward and inverse rendering, which allows estimating G-buffers from images, videos, and streams, and rendering realistic images, videos, and streams from G-buffers. Our key contribution is a general recipe for finetuning diffusion transformer (DiT) models into generative forward and inverse renderers. We show that the resulting models achieve high quality in both realistic generative rendering and intrinsic decomposition. We will make all our models publicly available. We believe that the design principles presented in this paper will benefit future research on controllable generative forward and inverse rendering.
Read the full abstract

All authors Zheng Zeng, Marco Salvi, Lifan Wu, Jan Novák, Daqi Lin, Saeed Hadadan, Yichen Sheng, Robert Pottorff, Shiqiu Liu, Ravi Ramamoorthi, Ling-Qi Yan, Miloš Hašan

Thursday 13 August

Graphics

Strand-based Hairstyle Generation via Large Reconstruction and Multimodal Models

Conghui Hao, Tao Huang, Yuefan Shen et al. (+3 more)

Creating high-quality strand-based hairstyles in current production pipelines remains heavily dependent on skilled artists and time-consuming manual authoring, making it costly and difficult to scale. Existing learning-based methods have advanced image-driven hair reconstruction, but typically require large, diverse training datasets, struggle to generalize to complex styles such as buns and ponytails, and often operate in representations that are not directly compatible with strand-based modeling, editing, and simulation. We present a novel automatic pipeline that combines the capabilities of Large Reconstruction Models (LRMs), Large Multimodal Models (LMMs), and classical geometry processing to generate high-quality strand-based hairstyles from single-view images. Our approach produces detailed, production-ready strand geometry without task-specific training or data collection and can handle a wide variety of hairstyles, including straight and curly hair, short and long styles, and challenging structured configurations such as ponytails and buns. Across this diverse set of examples, our method generates visually compelling strand-level reconstructions within only a few minutes, making it well-suited for integration into modern digital human workflows.
Read the full abstract

All authors Conghui Hao, Tao Huang, Yuefan Shen, Tongtong Wang, Zhongtian Zheng, Kui Wu

Graphics · Cross-listed from cs.CV

SCULPT: Subtractive Composition for 3D Part Generation

Sikuang Li, Chen Yang, Jiemin Fang et al. (+5 more)

Part-aware 3D generation aims to create digital assets that are coherent as complete objects while exposing structural parts for editing, material assignment, animation, and reuse. Existing methods impose this structure outside the native generation loop: segmentation-based methods partition an already generated shape, while additive methods synthesize parts from predefined layouts, boxes, or tokens and then reconcile them into a whole. The former preserves the generated geometry but fixes the object before part boundaries are determined; the latter exposes part cardinality but often leaves shared boundaries vulnerable to gaps, interpenetrations, and material discontinuities. In this paper, we propose SCULPT, a framework that addresses these challenges through subtractive composition. Given a complete object represented in a structured 3D latent space, SCULPT iteratively applies a joint split predictor to generate one extracted part together with the remaining object. The predictor performs a coupled denoising process conditioned on both the image and the current 3D state, so the extracted part and updated remainder are generated together rather than reconciled after generation. The joint split predictor processes both outputs on the union of their native sparse 3D supports, allowing neighboring supports to overlap rather than imposing a disjoint voxel partition. The rollout ends when the remainder support becomes empty or reaches a fixed safety cap, allowing the number of generated parts to adapt to each object within that bound. Extensive experiments demonstrate state-of-the-art geometry on PartObjaverse while preserving strong complete-object reconstruction after part assembly. Results on four dataset images, one text-to-image-generated input, and one real-world photograph further show fine-grained textured part decomposition beyond the benchmark.
Read the full abstract

All authors Sikuang Li, Chen Yang, Jiemin Fang, Jiazhong Cen, Yuhe Wei, Jichen Pang, Wei Shen, Qi Tian

Graphics

Blue Noise as a Lattice Gibbs Ensemble

Zhuoran Yi

We present an algorithm for generating blue-noise point sets that is simultaneously local and parallel, and whose output is a draw, up to a bounded error, from an explicit probability distribution. Methods that optimize point positions achieve high spectral quality but tend to couple all points globally, while tile-based methods, the main existing local approach, assemble their output from point sets constructed offline rather than generating it from scratch; we show that locality does not require giving that up. Concretely, we model blue noise as a Gibbs distribution over a lattice, with a pairwise penalty whose continuous parameters control repulsion strength, scale, and hardness. To sample this distribution locally, we trace each site's dependencies backward in time and truncate the trace to a bounded region known before sampling begins; tiles can therefore be generated independently in any order, with no communication between them. We stipple a 14557$\times$8418 James Webb Space Telescope image tile by tile, with peak memory under 51 MiB, set by the working window rather than the image dimensions. Spectral quality is competitive with existing methods at matched density, and the construction extends naturally to multi-class outputs.
Read the full abstract

Graphics · Cross-listed from cs.HC

More Than 63% of IEEE VIS Research Liable to be Retracted?! Ethics Approval Statements Protect Participants (and Researchers!)

Lonni Besançon and Tobias Isenberg

We analyzed the ethics reporting in 255 IEEE VIS papers from 2024 and 2025, as published in TVCG. This analysis arose from our experience as readers and reviewers of IEEE VIS papers that such reporting is frequently incomplete or missing, as well as from investigations in which we ourselves had to answer challenges regarding ethics approval in our own work. Visualization research naturally often involves human participants, yet ethics approval and informed-consent procedures are not always explicitly reported. In our corpus, 189 papers (74.1%) reported on work involving human participants. Only 6 of them (3.2%) reported to have obtained ethics approval, an approval identifier, and having received informed consent from the participants, while 26 (13.8%) reported at least ethics approval and informed consent. These omissions do not imply that the empirical work was unethical or lacked approval. They rather show that current reporting practices make ethical approval difficult to assess. Beyond our alarming - yet true - paper title, we wish to raise awareness on how authors themselves may eventually be at risk for not properly reporting ethics. We argue that VIS should adopt clearer and more standardized ethics-reporting practices to protect participants, authors, reviewers, and editors.
Read the full abstract

Graphics · Cross-listed from cs.CV

Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling

Kiseok Choi, Inchul Kim, Jaemin Cho et al. (+2 more)

Cone-beam computed tomography (CBCT) enables volumetric reconstruction from X-ray projections, but suffers from severe artifacts–especially beam hardening–when imaging materials with high attenuation such as metals. These artifacts arise from the polychromatic nature of X-rays and are not properly addressed by conventional monochromatic reconstruction algorithms. While recent neural representation-based methods offer improved reconstruction quality, they are computationally expensive and often impractical for deployment. We propose a novel physics-inspired, self-calibrating metal artifact reduction method that efficiently reconstructs 3D CBCT volumes while correcting beam hardening artifacts. Our method integrates a polychromatic X-ray projection model, material-dependent attenuation profiles, and system response modeling into a Gaussian Splatting framework. Unlike prior work, we eliminate the need for manual metal masks or strong prior assumptions, and we optimize both reconstruction parameters and X-ray spectral characteristics jointly during training. We further introduce a high-fidelity synthetic CBCT dataset generation pipeline validated on Monte-Carlo x-ray simulation toolbox and release new datasets with severe metal-induced artifacts to support the community. This is the first splat-based method for reducing beam hardening in CBCT. Extensive experiments on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art approaches in artifact suppression and reconstruction accuracy.
Read the full abstract

All authors Kiseok Choi, Inchul Kim, Jaemin Cho, Hyeongjun Cho, Min H. Kim

Graphics · Cross-listed from cs.CV

EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision

Andela Ilic, Rachel Schuchert, Yijing Jiang et al. (+1 more)

Understanding hand-object interaction from egocentric vision is essential for modeling how people physically engage with the surrounding world. Yet reasoning about physically grounded interaction requires estimating the forces acting on hands and objects, beyond localizing contact. We present EgoPHI, the first method that jointly estimates dense contact maps and 3D force distributions on hand and object meshes from a single monocular RGB image and object geometry. To address the lack of scalable ground-truth force annotations, we introduce a physics-based simulation pipeline that augments existing hand-object datasets with dense per-vertex force supervision. EgoPHI then learns dense 3D contact and force on interacting hand and articulated object meshes, extending vision-based force estimation beyond image-space or planar settings. Our evaluation on in-distribution and out-of-distribution benchmarks shows that EgoPHI improves force estimation over existing approaches while generalizing to unseen datasets. To evaluate sim-to-real transfer, we constructed two physical objects that capture dense object contact and force magnitude and used them to record a dataset of interactions from eight participants across diverse touch and grasp types. Our results demonstrate that EgoPHI recovers meaningful 3D contact and force distributions in simulated, out-of-distribution, and real-world settings, advancing egocentric hand-object understanding from contact localization toward physically grounded interaction reasoning.
Read the full abstract

All authors Andela Ilic, Rachel Schuchert, Yijing Jiang, Christian Holz

Graphics

Matrix-Driven Quartic Overhauser (QOVR) Surfaces Structural Framework: Continuity Limitations, Computer Graphics Algorithms, and Software Implementation

Hakan Üstünel

This study introduces the spatial and analytical construction of the Quartic Overhauser (QOVR) surface generation framework designed to resolve boundary alignment and localized shape modification constraints. This framework implements a variable parameter fourth degree novel architecture to achieve exact parameter isolation across orthogonal coordinate axes. The analytical pipeline integrates directional spline blending functions with symmetric spatial control matrices, ensuring that internal knot vector variations allow localized surface adjustments while preserving the absolute positional invariance of global edge boundaries. Computational verification confirms that while the current formulation satisfies explicit C^0 positional closure and C^1 tangent continuity conditions across the internal and boundary interfaces without triggering global curvature propagation, edge joint separation, or wave-like artifacts, C^2 curvature continuity is not maintained. As demonstrated by three-dimensional mesh models and colormap visualizations, the spatial intensity fields condense strictly within the immediate neighborhood of the modified element, verifying that the displacement effect decreases exponentially as the distance from the perturbed control points increases. This explicit decoupling preserves structural symmetry and boundary invariance across adjacent geometric patches, satisfying manufacturing and reverse engineering sealing criteria. Keywords: Quartic Overhauser surface; computer aided geometric design (CAGD); local shape control; geometric continuity; symmetric tensor products; computer graphics algorithms; software implementation framework.
Read the full abstract

Wednesday 12 August

Graphics

MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimation

Liangwei Li, Lin Liu, Jing Zhang et al. (+5 more)

In 3D anomaly detection (3DAD), most existing methods rely on Memory bank retrieval or reconstruction. However, memory-based methods are constrained by the coverage of stored normal features, while reconstruction-based methods may learn identity shortcuts that also reconstruct anomalous inputs well. These limitations motivate a density-oriented approach that evaluates whether a test sample follows the learned normal distribution. To this end, we propose MVFM-3DAD, a flow-based framework that reframes 3DAD as density proxy estimation over the normal data distribution. MVFM-3DAD introduces a Bidirectional Geometric Projector (BGP), whose forward process converts irregular point clouds into structured multi-view representations. The Flow-guided Density Proxy Estimator (FDPE) estimates a reference density for each view feature, after which the backward process of BGP maps these multi-view density estimates to their corresponding 3D points. Building on it, anomalous features can be identified by their terminal normality. Unlike conventional flow-based likelihood estimation, our formulation requires neither input reconstruction nor explicit Jacobian evaluation, yielding a simple and efficient anomaly-scoring mechanism. Extensive experiments show that MVFM-3DAD outperforms the strongest competing methods on Real3D-AD and MVTec3D-AD. Code is available at https://github.com/lil-wayne-0319/MV3D-AD
Read the full abstract

All authors Liangwei Li, Lin Liu, Jing Zhang, Xiaohui Du, Ruqian Hao, Xinwei Li, Hanzhe Liang, Juanxiu Liu

Graphics · Cross-listed from cs.HC

A Browser-Based Gesture-Driven Avatar Interaction Framework for Metaverse Onboarding Environments

Deepti Parachuri, Chhayank Sahu and Sameer Singh Choudhary

Avatar interaction shapes how engaging and immersive a metaverse experience feels, and for that interaction to feel natural, avatars need to respond to users without forcing them through a controller-based interface first. This paper describes a gesture-driven interaction layer built for a browser-based metaverse onboarding environment, where users explore a set of virtual rooms as an avatar and interact with embedded video, document, and quiz content using hand, arm, and head gestures instead of a keyboard or controller. The system combines real-time gesture recognition (Google MediaPipe) with two alternative locomotion techniques - hand-raise navigation and in-place walking - so users can trade off precision against physical immersion depending on the task. The contribution is the integration, deployment, and evaluation of these techniques as a single lightweight, web-deployable, controller-free interaction model, assessed through a structured internal onboarding session with five participants. We report what worked, what didn't, and the design trade-offs that came out of combining these techniques in one deployed system.
Read the full abstract

Tuesday 11 August

Graphics

A Geodesic Cut-Cell Prior for Neural Skinning

Wenchao Ma, Surya Dwarakanath, Yizhak Ben-Shabat et al. (+4 more)

We introduce cut-cell skinning, a geometric prior designed to augment data-driven skinning weight generation. While data-driven methods show promise in producing high-quality skinning weights, they often lack the generalizability of classic geometric approaches. To bridge this gap, we propose a geometric prior that can be robustly computed for in-the-wild meshes and is efficient for large-scale machine learning workflows. The key idea of our cut-cell skinning is a fast graph-based approximation of the volumetric geodesics distances, motivated by their importance in classic skinning weight computation. Our method achieves orders of magnitude speedup compared to optimization-based solvers and remains resilient to topological artifacts common in cage- or voxel-based alternatives. We demonstrate the efficacy of the cut-cell skinning prior by integrating it into recent neural skinning models, showing consistent improvements across existing methods and achieving state-of-the-art results. Project page: https://wenchao-m.github.io/CutCell.github.io/
Read the full abstract

All authors Wenchao Ma, Surya Dwarakanath, Yizhak Ben-Shabat, Dario Kneubühler, Haomiao Jiang, Sharon X. Huang, Hsueh-Ti Derek Liu

Graphics

WildFireGS: Physics-Based Wildfire Simulation in Large-Scale Semantics-Enriched Gaussian Splatting Forest Scenes

Nienke Driessen, Joris Rijsdijk, Sören Pirk et al. (+3 more)

Climate-driven environmental change is driving an increase in both the frequency and severity of wildfire events, making accurate simulation and prediction critical for effective risk mitigation and landscape management. While recent physics-based wildfire models achieve high realism by explicitly simulating combustion, heat transfer, and fuel dynamics, they remain largely restricted to synthetic environments with complete and idealized knowledge of forest structure, limiting their applicability to real-world environments captured via aerial imagery. To provide a pathway toward real-world wildfire digital twins derived directly from observational data, we present WildFireGS, a physics-based wildfire simulation framework operating directly on large-scale, semantics-enriched 3D Gaussian Splatting forest reconstructions. Our approach bridges learning-based scene reconstruction and environmental simulation by augmenting Gaussian primitives with semantics and material properties that encode vegetation type and fuel characteristics. We introduce a particle-based combustion model that operates natively on Gaussian representations, simulating ignition, heat transfer, combustion, and flame propagation across complex forest structures. This enables direct physics-based simulation of fire behavior on reconstructed real-world environments, without requiring conversion to explicit meshes or volumetric grids. We demonstrate the modularity of WildFireGS through a rain-driven cooling mechanism in terms of an energy-sink process to realistically model fire containment. Evaluations on synthetic scenes and real aerial forest captures show physically consistent wildfire behavior, reproducing characteristic dynamics including propagation scaling with vegetation density, wind velocity, and terrain slope. In addition, we validate our model through novel firebreak experiments and biomass loss estimation.
Read the full abstract

All authors Nienke Driessen, Joris Rijsdijk, Sören Pirk, Wojtek Palubicki, Dominik L. Michels, Michael Weinmann

Graphics · Cross-listed from cs.CV

The GENEA Challenge 2026: A Large-Scale Disentangled Evaluation of Speech-Driven Gesture Generation on the Seamless Interaction Dataset

Rajmund Nagy, Silvia Arellano García, Hendric Voss et al. (+4 more)

This preprint presents the results of the fourth GENEA Challenge, a large-scale human evaluation of five speech-driven gesture-generation systems trained by participating teams on the Seamless Interaction dataset of dyadic conversations. As in the 2023 GENEA Challenge, we used a disentangled evaluation methodology to assess motion quality and speech alignment without confounding between the two, and performed a dyadic mismatching study to isolate the effect of listening and reacting to the interlocutor. We additionally introduce a new semantic gesture-generation task and a text-mismatching evaluation methodology using the Grounded Gestures subset of the data. In total, we ran four large-scale user studies, collecting over 23,000 votes from 869 test-takers. In the motion-realism study, the dataset's filtered segments had substantially higher motion quality than all challenge submissions (68-95% pairwise winrate). In the speech-alignment study, the motion-capture segments provided a conceptual ceiling at 62% alignment score, with the top submission significantly behind at 32% and the rest only slightly above the 0% expected of an input-independent system. In the dyadic study, motion capture again set the ceiling at 65% appropriateness score, but no submission scored substantially above chance, indicating that the systems could not yet respond to the interlocutor. Finally, the semantic mismatching evaluation found highly expressive gestures in the dataset (test-takers identified the matching transcript 79% of the time), yet almost all submissions failed to generate semantically expressive motion, with the best achieving only an 8% appropriateness score. The collected votes and outputs will be made publicly available at https://genea-workshop.github.io/2026/challenge/ to facilitate reproducibility and further research.
Read the full abstract

All authors Rajmund Nagy, Silvia Arellano García, Hendric Voss, Mihail Tsakov, Taras Kucherenko, Youngwoo Yoon, Gustav Eje Henter

Graphics · Cross-listed from cs.CV

Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization

Ke Jiaxin, Juncheng Liu, Yi Wang et al. (+4 more)

3D Gaussian Splatting (3DGS) has recently enabled real-time novel view synthesis with impressive quality. However, it struggles to recover accurate surfaces under limited viewpoints and due to the inherent irregularity of Gaussian primitives. The resulting geometric errors are notoriously difficult to correct manually. To address these issues, we propose Gaussian Sculpting, a fully differentiable end-to-end framework for high-quality surface reconstruction. Our key insight is to anchor Gaussians onto an evolving differentiable surface, allowing them to guide signed distance field (SDF) optimization instead of extracting the surface only during post-processing. To enable stable gradient isolation during joint optimization, we design a bi-level training strategy in which the outer loop optimizes the geometry represented by the SDF, while the inner loop updates the Gaussians with the geometry fixed. We further impose constraints on Gaussian parameters to ensure consistency with the underlying surface, thereby improving both geometric and appearance fidelity during optimization. In addition, we introduce a multi-resolution subdivision scheme based on octree-like partitioning to preserve fine details while reducing memory consumption. Experiments on object-level scenes demonstrate that our method effectively removes redundant surfaces, recovers missing structures caused by limited viewpoints, and achieves strong reconstruction quality even at relatively low resolutions.
Read the full abstract

All authors Ke Jiaxin, Juncheng Liu, Yi Wang, Zhouhui Lian, Bin Liu, Shengfa Wang, Xiangjia He

Graphics

Amulet: Frame Extrapolation Through Sparse Layered Scene Representation and Adaptive Shading

Sebastian Künzel, Fabian Schmierer, Sergej Geringer et al. (+3 more)

We introduce Amulet, a rendering method that transforms a scene into a sparse, tiled and layered intermediate scene representation (cache) for high-frequency frame extrapolation. In contrast to reprojection-based techniques, Amulet explicitly rasterizes and stores potentially visible geometry in its layered image-space cache, allowing accurate shading and inpainting of newly disoccluded regions without hallucination. Our key contribution is a cache that is predictively filled with shading information for future views, amortized over multiple current frames. Novel views are synthesized by hierarchically traversing the cache front to back and refining stale or missing shading on the fly. Using a predictive, gradient-based scheduler that assigns lifetimes for each tile, we enable adaptive shading updates under motion and dynamic lighting. Amulet decouples the rasterization and shading rate from the refresh rate of the display. In many scenarios, our cache can use a single shaded frame to synthesize multiple extrapolated frames with only a few localized updates. In a typical application, we extrapolate a 60 Hz shading rate to a 240 Hz display. Amulet achieves up to 250 Hz at 4K resolution and is competitive with state-of-the-art frame generation methods, including DLSS and neural-flow approaches, in multiple metrics. Amulet explores the design space of sparse layered image-space representation. It enables accurate, non-neural multi frame extrapolation with explicit handling of disocclusions. Our findings show that Amulet can extrapolate many more frames than contemporary methods with high quality, rivaling latency-bound frame interpolation methods with similar quality in many scenes.
Read the full abstract

All authors Sebastian Künzel, Fabian Schmierer, Sergej Geringer, Guido Reina, Daniel Weiskopf, Dieter Schmalstieg

Monday 10 August

Graphics

Proximity-Preserving Neural Subdivision

Hassan Ugail

Classical subdivision schemes are widely used because they are local, repeatable, and analytically tractable. A single stencil defines the entire refinement rule, and the behaviour of the resulting operator under iteration is well understood. This uniformity, however, means that fixed stencils tend to underfit localised geometric features, such as sharp ridges or soft edges, where curvature is concentrated. Neural mesh refinement can adapt to such features, yet unconstrained vertex prediction usually lacks the structural behaviour required of a subdivision operator once the refinement rule is applied to its own output. In this work, we introduce Proximity-Preserving Neural Subdivision, or PNS for short. PNS is a trainable refinement rule that augments Loop subdivision with a small, bounded, curvature-gated correction expressed in a covariant local frame. The construction is designed so that, for any finite network weights, the operator is exactly equivariant under rigid motion, reproduces planar input exactly, and remains inside a quadratic proximity envelope around the Loop stencil. At planar valence-k stars, the linearised operator agrees with Loop, and it therefore inherits Loop's tangent eigenspaces and Reif spectral gap at that reference configuration. All of these properties are architectural and hold before any training takes place. Empirically, PNS improves the approximation of localised ridge features while remaining inside its prescribed proximity envelope under repeated subdivision. An unconstrained neural baseline, in contrast, achieves stronger one-step fitting but develops high-frequency artefacts and leaves the subdivision regime once iterated. The overall message of this work is that learning can be introduced into subdivision without abandoning the structural constraints that make subdivision useful as a geometry-processing primitive.
Read the full abstract

Graphics · Cross-listed from cs.CV

Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs

Yitong Mu

Film emulation reproduces the look of an analog film stock on a new digital photograph. We target its open-set form – matching any reference film frame from a single example – with a 3D lookup table (LUT) predicted from that reference. Real-time image enhancement predicts per-image weights over a fixed bank of 3D LUTs and blends them. We show this is a gated mixture of experts and inherits its failure: trained end-to-end against reconstruction, the gate collapses onto a single expert, so a bank of K LUTs delivers the capacity of one. An entropy term, the enhancement-setting analogue of mixture-of-experts load balancing, restores utilization and recovers about 1 dB PSNR. The deeper constraint survives: a fixed LUT basis is closed-set, freezing the achievable looks at training time. We therefore discard the basis and predict a single 3D LUT as a residual from a reference image (StyleLUTNet), trained by self-supervision on procedurally generated color transforms. The conditional design removes the gate and generalizes open-set to unseen film stocks without paired data or retraining. Around this color backbone we build Deep Analog, a film-emulation pipeline that adds histogram-based tone matching and a physics-informed optical renderer – multi-scale grain and per-channel halation driven by parameters an inverse network regresses from the reference. On 350 self-supervised pairs the color stage reaches 22.05 dB PSNR / 0.925 SSIM and the full pipeline 21.72 dB / 0.923; the color path runs in 5.2 ms at 1080p (192 FPS) and exports a portable .cube LUT for standard editing tools. A second degeneracy in conditional LUT training – residual-scale collapse – shares the root cause and yields a general principle: auxiliary regularization must stay subordinate to reconstruction.
Read the full abstract

Graphics

A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering

Louis De Oliveira, Anastasia Karpova, Georges Nader et al. (+4 more)

Over the past decade, microfacet-based BRDF models have formed the foundation of real-time rendering pipelines. Despite their widespread use, they often fail to reproduce subtle appearance effects arising from complex light-surface interactions, which have led to the emergence of specialized physics-based models for specific optical phenomena (e.g., diffraction, iridescence, multilayers). Although more accurate, these models lose versatility and lack performance for real-time rendering. Recently introduced, neural models have demonstrated their ability to approximate BRDF reference data coming from measurements, simulations, or even complex shading networks. However, most current neural models require relatively large networks, making them costly for real-time rendering. In this paper, we introduce a hybrid model that combines a GGX-type microfacet model and a neural model to leverage the best features of both representations. The neural component corrects the appearance approximated by the microfacet component, allowing much smaller network than in existing neural models. We show that, at identical memory cost, our model approximates measurements better than state-of-the-art neural models for a low evaluation overhead compared to a microfacet-based model. Furthermore, our hybrid model remains easily editable by artists and benefits from an important sampling scheme, making it attractive for both offline and real-time rendering.
Read the full abstract

All authors Louis De Oliveira, Anastasia Karpova, Georges Nader, Antoine Houdard, Pierre Mezieres, Damien Rioux-Lavoie, Romain Pacanowski

Graphics · Cross-listed from cs.RO

High Fidelity Capture, Reconstruction, and Transfer of Human Demonstrations for Robot-Assisted Bathing

Arjun S. Lakshmipathy, Jonathan P. King, Ethan Zuo et al. (+6 more)

Despite the demand for robots in high-value clinical tasks like bathing, contemporary systems still lack the safety and reliability required for complex, sustained physical interaction with humans. A key challenge hindering the development of such systems is that collecting, understanding, and effectively transferring highly dynamic, contact-rich human bathing demonstrations is difficult, even with modern motion and tactile sensing equipment. We present a straightforward, but effective framework for doing so with high fidelity by utilizing contact regions as a key processing primitive. We use our framework to build a dataset of bathing demonstrations performed by trained clinicians on human subjects. We then use this dataset to design and control an arm-mounted dexterous soft hand to perform bathing tasks on a mannequin using open- and closed-loop strategies. Our dataset is the first to provide high quality synchronized motion, shape, contact, and force during sustained, contact-rich human-human interaction, and our transfer strategies demonstrate effective use of these data across multiple levels of the robotics stack. All relevant materials will be publicly released to enable further advancements in physical human-robot interaction (pHRI) research.
Read the full abstract

All authors Arjun S. Lakshmipathy, Jonathan P. King, Ethan Zuo, Rohit Satishkumar, Hongyi Chen, Jeffrey Ichnowski, Dan Ding, Zackory Erickson, Nancy S. Pollard

Graphics · Cross-listed from cs.CV

View-Adaptive Renderer for View-Consistent 2D-to-3D Generation

U-Chae Jun, Jaeeun Ko and Jiwoo Kang

Reconstructing 3D shapes from a single image remains a fundamental yet challenging problem in computer vision. Traditional monocular 3D generation pipelines typically synthesize multiple views from a single input image before applying Neural Radiance Field (NeRF)-based reconstruction. However, inherent projective ambiguities often produce visual discontinuities across generated viewpoints, leading to inaccuracies in reconstructed 3D models. Current solutions either incur significant additional computational burdens or fail to adequately resolve practical inconsistencies between synthesized views. To address these limitations, we propose a novel viewpoint-adaptive neural rendering framework that enables robust 3D reconstruction even when given partially inconsistent multi-view inputs. Our approach introduces view-adaptive neural renderers that independently correct viewpoint-dependent errors while simultaneously sharing a global feature backbone to preserve structural coherence. Furthermore, we propose a self-attention fusion module that adaptively integrates multi-view information, ensuring geometric consistency without relying heavily on indirect regularizations or computationally intensive methods. Through extensive experiments, we demonstrate that our method consistently improves 3D reconstruction fidelity. Importantly, our approach achieves near state-of-the-art performance without diffusion-based SDS supervision, relying primarily on photometric rendering loss with lightweight attention regularizers. This balance between accuracy and efficiency makes the proposed framework highly practical for real-world applications.
Read the full abstract

Graphics

Smooth Motion Stitching via Laplacian Optimization in Rodrigues Vector Space

Ryosuke Higasayama, Hideki Todo and Jongseong Gwak

This paper presents a motion editing framework for smooth motion stitching based on Laplacian optimization in Rodrigues vector space. By representing joint rotations as continuous Rodrigues vectors, motion stitching is formulated as a temporal Laplacian optimization problem, enabling smooth transitions between motion segments while preserving characteristic temporal variations of reference motions. The proposed approach supports both intra-category replacement and cross-category motion stitching without relying on learning-based models or complex manual tuning, and is computationally efficient for interactive editing. Through a series of stitching experiments and comparisons with linear interpolation, we demonstrate that Laplacian editing produces stable and visually coherent transitions under a wide range of motion differences. Furthermore, an analysis of rotational continuity clarifies that rotation-axis inversions are rare in real motion data and explains why numerical instabilities observed in synthetic axis-flipping scenarios do not arise in practical motion stitching. These results highlight the importance of rotational representation in stabilizing temporal optimization and suggest that the proposed framework is well suited not only for animation authoring but also for motion analysis and future extensions incorporating perceptual or physiological cues.
Read the full abstract

Sunday 9 August

Graphics

Adaptive Volumetric Parameterization of Simply Connected 3-Manifolds with Applications

Zhiyuan Lyu, Qiguang Chen, Lok Ming Lui et al. (+1 more)

Volumetric parameterization, the process of mapping a 3-manifold onto a simplified volumetric domain, is important for many tasks in computer graphics and imaging science. However, most prior volumetric parameterization approaches have only utilized standardized domains such as a solid ball regardless of the overall shape of the given 3-manifolds, which introduces significant geometric distortion and affects the subsequent shape processing and analysis tasks. To overcome this issue, in this work we propose a novel volumetric parameterization framework for simply connected 3-manifolds. Specifically, the proposed framework jointly controls local shape and mass distortions, while adapting the target domain during the optimization process. It enables three progressively more flexible target-domain settings for the parameterization: a prescribed solid ellipsoid, a volume-normalized adaptive ellipsoid with variable radii, and a sea-embedded free-boundary domain. For each setting, the parameterization algorithm consists of a 3D quasi-conformality shape update, a diffusion-based density-equalizing update, and a geometric correction procedure for removing element foldings, thereby allowing for volumetric parameterizations with different desired effects. Experimental results are presented to demonstrate the effectiveness of our proposed framework. Moreover, our framework can be easily applied to multiresolution and localized adaptive volumetric remeshing, volumetric registration, and volumetric morphing. Altogether, our work provides a new way for the representation, processing, and analysis of 3-manifolds.
Read the full abstract

All authors Zhiyuan Lyu, Qiguang Chen, Lok Ming Lui, Gary P. T. Choi

Graphics

Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation

Lei Shu, Ying Jiang, Kui Wu et al. (+3 more)

Differentiable simulation is a key component in learning, control, and inverse problems, where gradients through nonlinear implicit solvers are required. Existing approaches either rely on unrolled automatic differentiation, whose memory grows with solver depth, or on equation-level implicit differentiation, which assembles global Jacobians and solves large sparse adjoint systems, discarding the locality of the forward solver – and differentiating the converged equation rather than the finite computation that actually ran. We propose solver-level differentiation, which differentiates the executed solver itself. When a solver is composed of block implicit updates, its discrete adjoint is obtained by applying the corresponding adjoint updates in reverse order, yielding a reverse-sweep formulation whose backward pass mirrors the forward solver. From an operator perspective, the forward pass realizes an approximate inverse through ordered local solves, and the backward applies its transpose through reverse local adjoint solves, constructing no global system. We instantiate this idea on Vertex Block Descent, yielding a differentiable solver whose reverse colored Gauss-Seidel sweeps are composed entirely of local $3\times 3$ adjoint solves. The backward matches automatic differentiation through the identical executed forward to machine precision at every solver depth, where the equation-level adjoint is off by 37% after one sweep; in a controlled same-codebase, same-GPU comparison it is 33x faster and uses 71x less memory than unrolled automatic differentiation; and the same construction is exact on projective dynamics and extended position-based dynamics. We scale differentiable elastodynamics to $10^6$ contact-coupled soft bodies (8M vertices) on one GPU. Overall, this work highlights solver structure as a practical organizing principle for efficient differentiable simulation.
Read the full abstract

All authors Lei Shu, Ying Jiang, Kui Wu, Yin Yang, Leonidas Guibas, Chenfanfu Jiang

Graphics · Cross-listed from cs.HC

FZ-VIS: A Visual Analytics Framework for Quantities-of-Interest-Aware Scientific Lossy Compression

Guoxi Liu, Yuxiao Li, Congrong Ren et al. (+6 more)

Modern scientific simulations generate massive volumes of data, making lossy compression essential for efficient storage and transmission. However, preserving critical quantities of interest (QoIs) under lossy compression is inherently data- and task-dependent, requiring domain scientists to navigate complex trade-offs between compression ratio and data fidelity. Exploring these trade-offs often involves large design and evaluation spaces, motivating human-in-the-loop approaches that combine interactive exploration with quantitative analysis. To address this challenge, we present FZ-VIS, an interactive framework for human-in-the-loop feature-oriented lossy compression design and visual analytics. FZ-VIS provides a web-based interface for rapidly generating and comparing compression configurations, along with integrated visualization tools for assessing reconstruction fidelity and QoI preservation through both visual inspection and quantitative metrics. We demonstrate the utility of FZ-VIS through case studies involving three representative user groups: novice users selecting compression methods, compressor developers examining internal pipeline behavior, and domain scientists investigating feature preservation. The case studies show how FZ-VIS helps users efficiently navigate complex design spaces and make informed decisions that balance compression performance with application-specific QoI requirements.
Read the full abstract

All authors Guoxi Liu, Yuxiao Li, Congrong Ren, Robert Underwood, Xin Liang, Bei Wang, Sheng Di, Franck Cappello, Hanqi Guo

Saturday 8 August

Graphics · Cross-listed from cs.DC

Evaluating and Improving Weak Scalability Analysis of Visualization Algorithms

Marvin Petersen, Jonas Lukasczyk and Christoph Garth

Research on visualizing large-scale datasets traditionally relies on empirical evaluation of scalability, determining the effectiveness of specific computation methods, algorithmic strategies, or implementations. Weak scalability, which assesses the algorithm's performance as problem size and computing resources increase, is a valuable indicator for a method's applicability at scale. However, sufficiently large data sets with increasing size are needed for weak scalability studies. To this end, it is customary to use simple scaling techniques to increase problem size by generating larger input data sets from a base data set. Nevertheless, many visualization algorithms' workload depends on factors beyond input size, such as input data complexity or output size, leading to inaccuracies in the attributed weak scalability. In this work, we highlight different common data scaling methods on multiple algorithms and data sets, recognizing that the suitability of scaling approaches varies across algorithms and data sets. We present a method that effectively mitigates the observed inconsistencies in workload increases for the different scaling methods in a shared-memory setting. With this work, we aim to further the discussion on how to evaluate and report scalable visualization research.
Read the full abstract

Graphics · Cross-listed from cs.CV

ASV3D: Adapting Diffusion-Based Single-View 3D Reconstruction with Extra Imagery

Y Huynh, Duc Thanh Nguyen, Thao Minh Le et al. (+1 more)

Reconstruction of 3D objects from a single image is a fundamental research topic in computer vision. The key challenge is the lack of information from critical viewpoints to complete 3D structures. Using an additional view may help to resolve the issue. However, there is no mechanism that can integrate the extra view into the diffusion-based single-view 3D reconstruction principle. We address this challenge by proposing ASV3D, a framework for adapting diffusion-based single-view 3D object reconstruction to test-time data with support from one additional image. We introduce two adaptation strategies: (i) a zero-shot adaptation scheme that leverages the auxiliary image to improve the reconstruction quality of an object without retraining, and (ii) an optimised adaptation scheme that further enhances visual fidelity and cross-view consistency via contrastive learning. We apply our ASV3D to improve two state-of-the-art diffusion-based single-view 3D reconstruction pipelines on both benchmark and real-world datasets. Results demonstrate that our approach consistently improves reconstruction accuracy and robustness under unconstrained multi-view inputs, outperforming the baselines in both quantitative metrics and human preference. We publish our code and the real-world object dataset on our project page at https://github.com/YNhuHuynh/ASV3D/tree/main.
Read the full abstract

All authors Y Huynh, Duc Thanh Nguyen, Thao Minh Le, Mohamed Abdelrazek

Graphics · Cross-listed from cs.HC

Marks, Channels, and Dead Ends: Stop Running Graphical Perception Studies and Start Modeling Visualizations as Images

Khairi Reda, Shambhawi Sharma, Luc Renambot et al. (+2 more)

Graphical perception studies are the visualization community's preferred tool for evaluating visualizations. By measuring how accurately people interpret arrangements of visual marks and channels, they aim to establish best practices for visual encoding. We argue that this model is fundamentally flawed, and no amount of additional empirical studies will fix it. Visualization theory frames effectiveness at the level of the encoder: which data-to-visual mappings work best in a given context. Human perception, however, operates as a fundamentally different decoder at the level of retinal images. This encoder-decoder asymmetry means that experimental results and guidelines can be poor predictors of perceptual performance. Moreover, the image reaching the visual system emerges from interactions among encoding rules, input data, and micro-design parameters–factors largely invisible to encoding theory. Consequently, small changes in data distributions or design variations can substantially alter perception even when the nominal encoding remains unchanged. We argue that visualizations should instead be studied as images and evaluated using computational models of human vision that take pixels as input. Such models capture the perceptual representations the visual system actually constructs, shifting evaluation toward the decoder rather than abstract encoding specifications. This approach is scalable, human-grounded, and sensitive to emergent image properties that both encoding theory and graphical perception studies miss. We first describe weaknesses of the current paradigm and propose a theory of visualization perception grounded in summary-statistical accounts of vision. We then show how image-based vision models can predict visualization discriminability in scatterplots while reproducing established results. We close by outlining a research agenda for vision-based visualization evaluation.
Read the full abstract

All authors Khairi Reda, Shambhawi Sharma, Luc Renambot, Fabio Miranda, Saeed Boorboor

Friday 7 August

Graphics · Cross-listed from cs.HC

Beyond the Good, the Bad, and the Ugly: Colormap Assessment through Data-Aware Perceptual Metric

Xi Duan, Yiwei Lin, Shiqing Xin et al. (+4 more)

Continuous colormaps are widely used to visualize scalar fields, and their quality is typically evaluated using measures such as discriminative power and uniformity. Existing measures primarily characterize the intrinsic perceptual properties of the colormap itself, largely independent of the underlying data distribution. In practice, however, user perception arises not from the colormap alone but from the visualization generated by mapping data values through the colormap. The perceptual differences that users actually experience depend jointly on the colormap and the underlying data. We propose a data-aware formulation that complements existing data-independent colormap assessment approaches. Rather than analyzing the colormap in isolation, we model the color-encoded visualization as a composite mapping from the spatial domain of the data to perceptual color space. This approach yields data-aware counterparts of established measures, including discriminative power, uniformity, and smoothness, as well as additional measures such as perceptual anisotropy and degeneracy. We validate the proposed measures against both the existing data-independent framework and empirical results from perceptual studies, extend the formulation to 2D colormaps, and demonstrate its integration into colormap optimization. An interactive system is provided for exploring colormap assessment under varying data distributions. Results demonstrate that our formulation offers a principled foundation for data-aware colormap assessment and design.
Read the full abstract

All authors Xi Duan, Yiwei Lin, Shiqing Xin, Aoying Wang, Yucheng Wang, Changhe Tu, Qiong Zeng