Papers

Gaussian-splatting proxies enable interactive rendering of volumetric medical scans, but a clipping plane exposes anatomy not constrained by external-view training and intersects primitives that conventional splatting can only keep or drop whole. We present XClipGS (eXact Clipping), which treats these as two separate problems: the render-time clip operator and supervision of the hidden interior. Under the local affine model used by EWA splatting, the ray integral of a half-space-restricted Gaussian factorizes exactly into its ordinary 2D footprint and a conditional Gaussian CDF whose argument is affine in pixel coordinates. The resulting closed-form per-pixel operator introduces no learned clipping parameters or auxiliary network and remains differentiable with respect to the primitive and plane. We use multi-distance reference views with varied clipping-plane axes and offsets to supervise the interior through the same operator. We also introduce a paired clipped/unclipped cut-face protocol with difference-referenced cut error (CDE) and culled-side leakage (Leak), because global image metrics dilute errors near the plane. On eight CT and MRI volumes with plane offsets not used for training, XClipGS attains the highest PSNR on every volume (33.56 versus 32.34 dB for ClipGS) while rendering at over 650 FPS, far above real time, versus 278 FPS. On voxel-axis cut-face views, it raises average band SSIM from 0.809 to 0.860 and leaks roughly 40 times less. Without retraining, it also achieves the best average across all four metrics on arbitrary-normal planes; on a fixed interior, it matches RaRa's face fidelity with about 16 times less leakage. Project page: https://gaozhongpai.github.io/XClipGS/

Solar Radiation Pressure (SRP), the force exerted by photons emitted by the Sun, is one of the main non-gravitational perturbations affecting spacecraft trajectories, making its accurate modeling essential for high-fidelity orbit propagation. While physically-based ray-tracing models improve SRP accuracy, their computational cost becomes a limitation during numerical integration, where the SRP force must be evaluated repeatedly throughout the trajectory propagation. This paper investigates the integration of high-fidelity SRP models into orbit propagation through two complementary contributions: a Vulkan-based GPU implementation that accelerates direct SRP evaluation, and an extension of the SRP model to account for the dynamic orientation of solar panels. These contributions are evaluated independently through orbit propagation experiments, while a precomputed SRP interpolation strategy (SPAD) is included as an alternative approach for reducing computational cost through offline sampling and interpolation. Numerical validation shows that the Vulkan implementation preserves the accuracy of the original OpenGL-based method, showing relative differences below $5\times10^{-4}$ while achieving speed-ups of up to 9.4 for individual SRP computations and up to 15.2 for complete orbit propagation, particularly for geometrically complex spacecraft. The movable solar panel model shows that neglecting panel motion can produce significant long-term propagation errors, especially for spacecraft with large articulated solar panels, while introducing only a moderate computational overhead. Based on the experimental evaluation, this work concludes with practical guidelines for integrating high-fidelity SRP models into orbit propagation frameworks, identifying the scenarios under which interpolation-based methods are sufficient and when online high-fidelity SRP computation is justified.

Trait-induced merge trees (TIMTs) provide a robust topology-based method for selecting and browsing feature level sets in multivariate data by analyzing the distance field induced by a user-specified trait in attribute space. Existing TIMT computations typically sample this distance field at mesh vertices and assume piecewise-linear interpolation, although the Euclidean distance-to-trait function is generally not piecewise linear on the original mesh. As a result, the resulting merge tree may miss zero-valued features and may perturb the locations and values of minima and merge events. We study the exact computation of TIMTs for piecewise-linear bivariate fields, focusing first on point traits. We show that the restricted sublevel sets inside each tetrahedron are convex and therefore have trivial local merge-tree structure, implying that global topological changes arise only through gluing across simplex boundaries. Based on this observation, we construct a weighted graph whose merge tree is isomorphic to the exact merge tree of the induced distance field. We further relate TIMTs to Jacobi sets, showing how nonzero edge events of the TIMT are localized by the singular structure of the underlying bivariate map. We establish a theoretical upper bound on the error of the vertex-sampled linear interpolation, expressed in terms of the maximum length of projected mesh edges in the range. We discuss extensions to line, line-segment, and finite point-set traits, and implement the method robustly using CGAL and VTK, demonstrating results on both synthetic and real-world datasets.

Real-to-sim (R2S) depends on scene representations that render observations along robot ego trajectories, yet dense multi-view capture limits per-environment real-image capture-count efficiency, and sparse human capture can leave behavior-scoped robot views under-supported. Camera-controlled synthesis can fill missing views, but its use in R2S requires behavior-admissible queries and capture-anchored structural conditioning. We present R2S-EGO, which couples a simulator-derived robot proxy that represents the behavior-scoped executable query domain with a capture-anchored geometry proxy that supplies scene-specific structural conditions. Within this domain, fixed- budget selection targets current support deficits for which geometry support is available. The generated observations are assimilated as pseudo-observations to refine the visual asset, while real captures remain anchors. The fused geometry proxy also supplies the scene collision surface, which is refreshed between rounds. Together, these updates refine the existing simulation scene while its robot dynamics and control stack stay fixed. Across 48 frozen Unitree G1 ego views in three Replica scenes, six-view R2S-EGO reaches 19.062 dB PSNR, compared with 14.226 dB for the strongest reported R2S baseline. Across five paired policy-training seeds, R2S-EGO achieves 82.5% +/- 6.8% real-G1 sitting success, compared with 10.0% +/- 10.5% for GaussGym.

3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation. However, the method's reliance on structure-from-motion initialization and photometric optimization can lead to suboptimal geometric reconstruction, particularly for objects with high specularity. In this work, we investigate the integration of geometric priors, in the form of predicted normal and depth maps, into the 3DGS framework to improve the reconstruction quality. We analyze the effect of incorporating these priors into GS-based methods and our evaluation reveals that multi-view predictions, as they are done by the recent visual geometry grounded transformer (VGGT), outperform single-view alternatives. A major factor is the existence of a confidence map for the estimations, which comes as a by-product of multi-view models and which can significantly improve the effectiveness of priors by weighting each prediction appropriately. Extensive experiments on standard benchmarks show consistent improvement in reconstruction quality and significant gains in complex scenes including specular objects.

Efficient representation and rendering of large-scale sparse volumetric data remain challenging in scientific visualization, as meaningful structures often occupy only a small fraction of the spatial domain. While direct volume rendering (DVR) provides high-quality visualization, its computational and memory costs scale poorly with data size. Recent advances in 3D Gaussian Splatting (3DGS) address this challenge by representing volumetric scenes with compact geometric primitives, enabling efficient, high-fidelity rendering. However, existing 3DGS-based methods learn from DVR rendered images rather than raw volumes, leading to information loss and limiting flexible transfer function control for interactive exploration. To address these limitations, we propose ESVR, an ellipsoid-based sparse volume rendering framework that directly learns and renders volumetric data in 3D space. Our method combines differentiable ellipsoidal primitives with bounded support, structure-aware primitive learning with complementary pruning, and a per-primitive ray sampling strategy for fast and accurate transfer function mapping. To support large-scale datasets, we further introduce a chunk-based optimization scheme with ghost ellipsoids, providing boundary context during training. Across large sparse datasets, ESVR achieves up to four orders of magnitude compression and real-time rendering at 43-223 FPS while maintaining competitive reconstruction quality.

Graphical Abstracts (GAs) visually summarize the key findings of academic papers, playing a crucial role in facilitating the understanding of research content. Recently, advancements in vision-language models and image generation models have enabled the automatic generation of scientific figures based on paper content. However, most conventional methods output the generated results as raster graphics, making post-editing (e.g., text modification and layout changes) highly difficult. This poses a significant challenge, as they are unsuitable for the iterative figure revision process inherent in paper writing and peer review. To tackle these challenges, we define the novel task of generating editable GAs from paper content and propose GenGA, a new GA generation framework that directly produces figures in vector format. By generating figures as a collection of vector elements with a hierarchical structure, GenGA produces outputs that can be seamlessly imported into existing drawing tools for intuitive, element-level editing. Furthermore, we introduce the Structural Independence Coefficient (SIC), a metric that quantifies the editing simplicity of a figure based on the degree to which local modifications propagate to other elements. Experimental results show that GenGA achieves superior editing simplicity compared to conventional methods, and even surpasses human-authored GAs in conciseness and semantic alignment. We also validate SIC as an effective metric correlated with manual editing costs. This study fundamentally redefines GA generation as an editable vector graphic generation problem grounded in the practical workflows of researchers, significantly promoting effective scientific communication.

Immersive exhibitions increasingly combine large-scale projections with mixed reality (MR) head-mounted displays (HMDs), but how users perceive transitions across these heterogeneous visualization environments remains underexplored. We investigate cross-reality (CR) object- and scene-level transitions in a hybrid immersive art installation spanning projection, augmented reality (AR), and virtual reality (VR). In a within-subjects study (N=24), we compared a calibrated condition with a bundled inconsistency condition introducing noticeable differences in spatial alignment, visual appearance, and cross-device latency. This contrast was used not to establish perceptual thresholds or hardware targets, but as a diagnostic probe to make transition disruptions more perceptible and discussable. The inconsistency condition reduced presence and increased workload. Interviews showed that spatial misalignment disrupted action-outcome predictability, appearance mismatch reduced aesthetic coherence, and latency weakened perceived responsiveness. Effects also varied by asset type: rigid static assets exposed inconsistencies more clearly, animated skeletal assets shifted attention toward motion, and particle effects often masked small discrepancies. These findings clarify how users perceive projection-MR transitions and support asset-aware design strategies for coherent hybrid immersive art. We also release HUICRSync, an open-source Unreal Engine plugin for prototyping projection-MR CR experiences.

Replicating real-world environments into simulation by realistic visual representation like NeRF and 3D Gaussian Splatting (3DGS) has emerged as an effective strategy to reduce the sim-to-real gap in robot learning. However, implementing object articulation during the real-to-sim process is still a challenging task. Existing motion tracking or learning based articulation methods shows low success rates on complex kinematic structures having multiple joints. Furthermore, those methods require scan of dynamic motion of objects, which makes reconstruction process much complicated. In this work, we propose the first end-to-end pipeline that reconstructs simulation-ready assets with accurate articulation from a single static object video input through suggestion based human-in-the-loop process. Our approach exports a hybrid representation combining 3DGS for photorealistic rendering and mesh-based geometry for physical interaction. In the reconstruction process, our pipeline performs convex decomposition followed by user grouping for intuitive part segmentation, subsequently binding 3D Gaussians to the corresponding mesh parts. An Automatic Joint Suggestion Algorithm then calculates candidate joint axes from local boundary geometries and presents them to users for efficient articulated asset reconstruction. We have shown that our method achieves precise articulation results on partnet-mobility-v0 dataset and real objects. Additionally we presented a potential usage of our framework on robot learning, deploying the reconstructed assets in Unreal Engine and NVIDIA Isaac Sim, demonstrating real-time dexterous hand manipulation tasks.

X-ray computed tomography (CT) suffers from severe metal artifacts when high-attenuation objects such as dental fillings or orthopedic implants are present. These artifacts originate from the polychromatic nature of X-rays, where attenuation varies strongly with photon energy and material composition, breaking the monochromatic assumption used by conventional reconstruction algorithms. Recent neural rendering approaches attempt to address this mismatch through differentiable polychromatic projection models, but they still struggle with smoothness bias, loss of fine structures, and prohibitive computation when extended to large-scale cone-beam CT. We introduce a splat-based metal artifact reduction framework that incorporates a physically grounded polychromatic forward model into a continuous Gaussian representation for cone-beam CT. Each Gaussian encodes the energy-dependent attenuation of the underlying material using a compact material parameterization, which enables efficient joint optimization of geometric and material properties without relying on a metal mask. This compact attenuation formulation captures the essential variation across biological tissues and metallic implants, allowing our model to explain metal-induced nonlinearity while preserving high-frequency structure. Experiments on simulated and real cone-beam CT scans show that our method converges significantly faster and suppresses metal artifacts more effectively than existing reconstruction and neural field-based approaches.

X-ray computed tomography (CT) reconstructs volumetric representations of objects from projection images obtained by transmitting X-rays through a target. Recent splat-based tomography, which represents a volume as a continuous distribution of 3D Gaussians, has demonstrated both high reconstruction quality and fast convergence in cone-beam sparse-view CT. However, when deployed in real CT systems with limited and non-uniform view distributions, we observe distinctive streak and strip artifacts that are far more pronounced than in conventional reconstruction methods. Through detailed analysis, we show that these artifacts primarily originate from pose inaccuracies in the acquisition geometry rather than from view sparsity itself. We revisit pose sensitivity in the splatting formulation and derive a stable gradient-based framework that jointly refines geometric parameters during reconstruction. Our study not only identifies how pose perturbations propagate through the differentiable projection operator but also reveals why splat-based CT is particularly vulnerable to geometric misalignment. The resulting formulation remains lightweight and easily integrable into existing pipelines while substantially improving reconstruction fidelity under real-world sparse-view conditions.

Direct Time-of-Flight (dToF) sensors provide highly accurate metric depth and are more robust than indirect ToF systems in challenging real-world conditions. However, their high manufacturing cost and limited photodiode array size produce depth maps that are extremely sparse, low-resolution, and noisy, making them unsuitable for VR/XR, robotics, and 3D perception tasks that require dense metric depth. Existing monocular and depth completion methods struggle to handle the unique sampling patterns and hardware artifacts of dToF devices, and their performance often deteriorates significantly under severe sparsity or noise. We present a generalizable framework for dense metric depth completion from sparse dToF measurements, capable of operating across diverse sensor types, sparsity levels, and noise conditions. Our model employs a depth-guided dual-branch Vision Transformer encoder that processes RGB images and sparse dToF measurements separately, while a masked joint attention module allows depth tokens to reliably guide image features without being overwritten by them. A lightweight decoder reconstructs dense metric depth efficiently, without diffusion-based or refinement-heavy post-processing. To address the scarcity of paired training data, we introduce a comprehensive dToF simulation pipeline that reproduces the characteristics of flash, sub-VGA flash, and rotating sensors, including hardware-induced degradation, irregular sparsity, and realistic noise distributions. Trained entirely on synthetic data, our model achieves strong zero-shot generalization across 6 datasets and 3 real dToF devices, outperforming state-of-the-art approaches in both accuracy and computational efficiency. This establishes a robust and practical solution for dense metric depth completion from sparse direct ToF sensors. Our code and models are open-sourced. See https://vclab.kaist.ac.kr/cvpr2026p3.

Creating photorealistic 3D human avatars with realistic upper-body motion remains challenging. Existing approaches either focus on the head and overlook hand gestures, or reconstruct the full body but fail to preserve fine-grained facial fidelity and hand pose accuracy. As a result, current methods struggle to capture the subtle dynamics of facial expressions and hand gestures that are crucial for natural human communication. While methods based on full-body parametric models enable avatar reconstruction from monocular or multi-view inputs, they often lack accurate facial animation and detailed hand articulation. To address these limitations, we propose MVFGA, a novel multi-view-consistent pipeline for generating realistic upper-body avatars. Our approach models the face and hands separately and fuses them with a parametric upper-body mesh model, enabling the capture of fine-grained facial expressions and hand poses for accurate upper-body avatar reconstruction. We then splat 3D Gaussians onto the obtained mesh, enabling high-quality rendering of dynamic avatars from novel viewpoints. Furthermore, we introduce MVFGA-MoCap, a multi-view upper-body motion capture dataset featuring controlled facial expression sequences, diverse hand gestures, and free-form communication. Experiments show that MVFGA generates visually realistic avatars with high-fidelity facial expressions and hand motions, outperforming baselines for upper-body avatar animation. Project page: https://dfki-av.github.io/MVFGA/

3D Language Gaussian Splatting embeds open-vocabulary language features into 3D Gaussian Splatting, providing an efficient explicit representation for text-driven 3D scene understanding. However, existing methods are limited to indoor or small-scale scenes, and tend to fail in Unmanned Aerial Vehicle (UAV) outdoor scenes, where severe occlusions and long distance viewpoints often lead to incorrect semantic activations and missing target responses. In this paper, we present OutLangSplat which adapts language Gaussian representations to UAV outdoor scenes by improving feature representation and aggregation reliability. For the feature representation, a 2D-3D dual-branch representation with region-based alignment and fusion is designed to improve spatial consistency, reducing incomplete target responses and background misactivations. For the feature aggregation, we introduce a training-free contribution and consistency-aware Gaussian feature aggregation strategy that leverages pixel contribution reliability and cross-view semantic consistency to suppress unreliable responses from noisy viewpoints. A new dataset is provided by manually annotating various objects on four real-world public UAV outdoor scene datasets. To the best of our knowledge, it is the first accessible dataset of open-vocabulary 3D scene understanding for UAV outdoor scenes. Quantitative evaluations and ablation studies demonstrate that OutLangSplat outperforms SOTA methods on both open-vocabulary semantic segmentation and instance localization tasks. The datasets and codes will be open-sourced.

Established channel effectiveness rankings primarily assess magnitude estimation accuracy in complete chart contexts, often neglecting other perceptual tasks such as discriminability, separability, and pop-out. To address this gap, we conducted crowdsourced experiments on seven core visual channels (position, length, tilt, area, curvature, luminance, and saturation) using primitive visual stimuli, a set of visual marks without chart-specific scaffolding to isolate channel-level variation. We evaluated these channels across four perceptual tasks (accuracy, discriminability, separability, and pop-out) and found that channel effectiveness is fundamentally multi-dimensional, with rankings shifting substantially across tasks. For instance, while spatial channels maintain an overall advantage, accuracy depends strongly on whether a fixed spatial anchor is available. Discriminability varies dramatically across channels and value ranges, a pattern we formalized with a novel Anchored Harmonic Weber model. Pairwise channel interactions are often strongly asymmetric. Finally, we identify a dissociation between estimation accuracy and preattentive detection: length shows only moderate detection effectiveness despite top-tier accuracy, while area achieves the highest detection rates despite poor quantitative accuracy, though the latter advantage may partly reflect stimulus-level cues. We synthesize these findings into a scenario-driven perspective for context-sensitive channel selection.

Seam carving is a classical content-aware image resizing operator that modifies the width or height of an image by repeatedly removing (or inserting) seams, i.e., 8-connected monotonic paths of pixels of locally minimal importance. Because seams bend around salient content rather than uniformly scaling or cropping it, the operator preserves vital image structures while discarding (or duplicating) low-energy regions. This article describes a C++ implementation of the operator that follows the original formulation of Avidan and Shamir (2007), including the optional forward-energy criterion subsequently introduced by Rubinstein, Shamir and Avidan (2008). The implementation supports image reduction, image enlargement via ordered seam insertion, multi-pass enlargement for large scale factors, a user-supplied weight mask for object protection and removal, along with dumping of energy maps and visualisation of seams. We detail the algorithm, its parameters and its computational complexity, discuss design choices with respect to the original descriptions, and illustrate the behaviour of the operator on natural images.

LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We introduce TraceCAD, a recovery layer that links requested features, modeling steps, failure evidence, and candidate outcomes as persistent state. TraceCAD diagnoses likely faulty operations, searches bounded edits in their dependency regions, validates candidates through execution and preservation checks, and retains successful and failed repair outcomes in reusable skill memory. On DeepCAD-derived benchmarks with 200-model ablations and a 1K-model comparison, TraceCAD achieves competitive geometric quality in terms of IoU, Chamfer distance, and Hausdorff distance. Removing persistent state nearly halves recovery score; removing localized search more than doubles geometric regression and doubles code-agent invocations. Initializing the skill store on disjoint training models further reduces retries, token cost, and latency. These results demonstrate that persistent, localized, and reusable recovery improves final CAD quality and repair reliability.

Audio-driven 3D facial animation aims to synthesize realistic and temporally coherent motions from speech. Despite notable progress in lip synchronization, weakly correlated dynamics, including eyebrow movements, eye blinks, and head motion, which are essential to photorealistic facial animation, remain difficult to model faithfully and often appear static or unnaturally repetitive. We attribute this limitation to three factors: (a) insufficient conditioning for weakly correlated dynamics; (b) the limited ability of deterministic regression to capture diverse motion patterns; (c) data bottlenecks from unreliable upper-face pseudo-labels and limited dataset diversity. To address these issues, we propose SubtleTalk, a framework for generating natural and controllable weakly correlated facial dynamics via multi-condition modeling and residual flow matching. First, to compensate for the limited guidance of speech alone, we introduce interpretable controls, including prosody, regional intensity, and Valence-Arousal signals, to explicitly capture the timing, magnitude, and affective variation of weakly correlated dynamics. Second, to overcome the limited expressiveness of deterministic regression, we build residual flow matching based on a stable speech-driven motion prior, allowing the model to capture stochastic deviations beyond deterministic prediction. Third, to alleviate the data bottleneck, we construct SubtleTalk-Face, a large-scale 3D facial animation dataset comprising about 3,900 identities and 74 hours of data, built via a simple and scalable pseudo-labeling pipeline and featuring improved upper-face tracking and frame-level VA annotations. Extensive experiments demonstrate that our method significantly improves the realism and diversity of weakly correlated facial dynamics while preserving accurate lip synchronization.

Asked to animate the same modern artwork under different random seeds, a text to video model returns visibly different films, one reading per seed. Because modern art is ambiguous by intent, this disagreement is signal, not noise. Yet prevailing uncertainty quantification (UQ) collapses a set of generations to a dispersion scalar that says how much the seeds differ but not how: it cannot tell a compact interpretation from a dominant reading plus an outlier, two competing modes, or diffuse instability, nor whether the set still contains a rendering faithful to the original. We present the first study of the structure of generative uncertainty for modern art animation, and a reusable protocol for identifying source blind multiseed uncertainty: a suite of seven source blind and six reference aware estimators; a distributional profile (robust spread, outlier influence, explicit topology, multimodality, anisotropy, leave one seed influence, reference coverage); a distribution model ablation (vMF, Kent, ACG, Student t, kernel, mixture); eight identification questions; and an artwork level statistical protocol. We build the first corpus: 250 modern artwork captions rendered by Wan2.1 14B under four seeds (1000 videos) across 4 encoders, artworks withheld from generation. As a diagnostic the protocol succeeds: it classifies seed set topology at balanced accuracy 0.98 (chance 0.25), isolates the outlier configuration at AUROC 1.00 where a scalar reaches only 0.35, and splits high uncertainty artworks into reference covering (n=97) and reference missing (n=56) diversity, reliably from three seeds and across encoders.

Designing narrative-grounded interactive experiences remains labor-intensive because interactive content must align with the underlying world implied by the narrative. Existing approaches formulate problems such as narrative planning, scene generation, and gameplay generation, each constructing computational representations tailored to specific downstream tasks rather than explicitly reconstructing and maintaining the persistent world that grounds them. We investigate reconstructing explicit persistent worlds from narrative descriptions as the central computational objective for narrative-grounded interactive realization. Rather than treating the world as an implicit by-product of downstream generation, our approach reconstructs and maintains persistent entities, locations, semantic relationships, and evolving world states while inferring only the contextual information required to support coherent interactive experiences. To investigate this perspective, we develop a reference prototype that reconstructs structured persistent world representations from narrative descriptions and subsequently instantiates playable tile-based environments. Through three representative case studies spanning a procedural scenario, an original fantasy narrative, and an adapted public-domain story, we demonstrate the feasibility of reconstructing persistent worlds and show how a shared world representation supports coherent gameplay while remaining grounded in the source narrative. By explicitly reconstructing persistent worlds prior to interactive realization, this work bridges computational narrative understanding and interactive content generation, providing a semantic foundation for AI-assisted game authoring, mixed-initiative design, educational simulations, and narrative-grounded interactive experiences.

This paper introduces PTI (Persistent Traversal Identity), a hierarchical symbolic addressing system for digital color derived from the recursive binary subdivision of the RGB color cube. Standard hierarchical color processing systems organize colors via recursive space partitioning but conventionally discard the traversal path once computation is complete. PTI formalizes the preservation of that traversal path as a persistent symbolic identifier. The resulting address is a finite sequence of eight-valued digits from the set {0, ..., 7}, each encoding the octant selected at one level of subdivision. Concatenated, they constitute a lossless alternative representation of any 8-bit-per-channel RGB color. PTI is structurally equivalent to the Morton (Z-order) code of a color interpreted as a sequence rather than an integer, and its construction algorithm is the octree traversal procedure of classical octree quantization, as established by Gervautz and Purgathofer. PTI does not introduce a new color space, nor does it claim to improve upon these foundational methods. Its contribution is a color representation that is simultaneously machine-precise and hierarchically interpretable, revealing a color's family lineage directly from its address structure. The same 8-digit address decodes losslessly to RGB and reads compositionally as a named sequence of weighted color directions. PTI's well-defined prefix semantics support direct address operations suited to color catalog organization, truncation-based image-processing routines, and structured exploration of colors. The address structure invites further operations beyond this. A simple one, successively rotating the address by one digit position, creates structurally harmonious color palettes derived directly from the geometry of the RGB cube, never leaving RGB.

We present a generative framework for the constrained design of $D_{2h}$-symmetric triply periodic minimal surfaces (TPMS) with low residual mean curvature. Existing TPMS design pipelines either explore a limited set of canonical analytical families or rely on computationally expensive numerical procedures, making it difficult to efficiently generate diverse candidates under geometric and/or mechanical requirements. Our approach learns a distribution of solver-generated TPMS in a compact Fourier space where periodicity and $D_{2h}$ symmetry are guaranteed by construction. This representation eliminates the need for a learned geometric decoder and enables the training of an effective diffusion model that generates low-mean-curvature candidates conditioned on sparse geometric constraints, selected homogenized elastic properties, or their combination. A subsequent coefficient-space refinement further reduces the residual mean curvature. Experiments show that our approach outperforms trigonometric, SDF-based, and standard Fourier-space baselines and enables controllable, high-quality generation under geometric and low-dimensional mechanical constraints. Overall, the proposed framework provides a compact and efficient design space for generating near-minimal periodic structures under user-specified requirements.

Force-Directed Placement (FDP) is a widely used approach for network visualization, yet scaling it to massive graphs while preserving clear community structures remains a major computational and visual challenge. Existing approximation methods often rely on auxiliary data structures (e.g., spatial trees), which introduce substantial memory overhead; furthermore, traditional power-function-based forces frequently fail to separate dense clusters effectively. In this paper, we present a negative sampling-based algorithm that achieves O(|E|) time complexity with a low memory footprint, without requiring complex multi-level representations. In a first step, we introduce a linearly normalized degree-weighting scheme, which, combined with short-range bounded $t$-distribution forces, effectively untangles dense structures and enhances visual cluster separation. To optimize for this formulation efficiently, we introduce an edge-centric negative sampling strategy that naturally reconstructs the global degree-weighted objective. Furthermore, we design a lock-free, bundle-based parallelization scheme that leverages the sparsity of stochastic updates to achieve significant speedups while mitigating access conflicts. Comprehensive evaluations on 12 large-scale graphs demonstrate that the proposed method outperforms state-of-the-art algorithms in neighborhood preservation and cluster separation. Compared to existing baselines, our method reduces memory consumption by 72% on average and leverages simple GPU parallelism to generate a high-quality layout for a graph with 4 million nodes and 34 million edges in below 10 seconds.

Part-level 3D generation has recently attracted increasing attention for producing structured and editable 3D assets. However, existing methods typically decompose objects according to functional semantics rather than the editable material boundaries (e.g., fabric, wood, metal) required in practical 3D applications such as interior design. Additionally, current methods often generate parts independently, causing computational costs to scale linearly with the part count. To address these limitations, we present PartMat, an efficient material-aware 3D part decomposition pipeline that represents multi-part geometry with a single global latent. Given a reference image and a single whole-object geometry, PartMat decomposes the object into parts that follow material boundaries. First, we propose PartVAE to learn such a unified representation and decode all material parts in a single forward pass, thereby decoupling inference cost from the number of parts. Second, with this representation, a diffusion model is trained for part generation and refined via reinforcement learning for accurate material assignment and overlap suppression. Finally, to recover fine-grained geometric details, we introduce a sparse-voxel flow-matching model with part attention for geometry post-processing. Extensive experiments demonstrate that PartMat significantly outperforms existing baselines in material-aware decomposition accuracy and achieves comparable geometric quality, while maintaining efficient inference.

Ptychography is a powerful lensless imaging technique capable of approaching the diffraction limit, yet its performance is increasingly constrained by non-ideal detection hardware. In photon-limited measurements, weak high-frequency diffraction signals often overlap with spatially heterogeneous detector noise, whereas most reconstruction algorithms still treat the detector as an ideal measurement plane. Here, we introduce detector-informed measurement consistency into ptychographic reconstruction. By calibrating the pixelwise sensor response, the method construct a spatially resolved confidence map and embed it into the iterative amplitude constraint, allowing unreliable detector residuals to be down-weighted while preserving physically meaningful diffraction information. Experiments across transmission, reflection, and weak biological phase imaging show improved diffraction-data quality, an approximately twofold signal-to-noise ratio (SNR) enhancement, and reconstruction approaching the Rayleigh limit with a measured (k)-factor of about 0.65. Compared with previous advanced denoising methods, the proposed framework achieves a better balance between suppressing detector-induced background and preserving structural diffraction information. These results show that detector reliability can be used as an in-loop physical constraint to extend the performance of ptychographic imaging with imperfect sensors.

Ptychography is a powerful lensless imaging technique that overcomes conventional numerical aperture limits to achieve diffraction-limited resolution. While routine at high-brilliance synchrotron facilities, its application to laboratory-scale sources is primarily limited by low photon flux. Under these conditions, the wide dynamic range of diffraction signals presents a critical bottleneck where detector bit-depth limitations hinder the simultaneous recording of low-frequency intensity and high-frequency details. Currently, most high-dynamic-range (HDR) imaging methods enforce strict radiometric linearity, assuming the fused intensity must be linearly proportional to the squared modulus of the wavefront to satisfy Poisson likelihood models. In this paper, we introduce a multi-scale non-linear fusion approach into the ptychographic pipeline, demonstrating that strict linearity is not a prerequisite for accurate reconstruction. This method mitigates the traditional trade-off between noise suppression and physical fidelity, enables robust imaging under strong dispersion, and significantly broadens the effective spectral bandwidth.

An interlocking assembly is an assembly in which component parts are connected purely through their geometric arrangement, without relying on external connectors such as glue and nails. Such assemblies have been widely used in a variety of real-world applications due to their structural stability. The problem of generating interlocking assemblies is generally formulated as a shape decomposition problem, where a target 3D object represented as a voxel grid is partitioned into a prescribed number of interlocking pieces. We observe that generating interlocking assemblies is inherently a sequential decision-making problem, where an agent repeatedly decides which piece each voxel should be assigned to. Inspired by the observation, we propose the first reinforcement learning framework RL-Lock for generating interlocking assemblies, without relying on handcrafted search heuristics as existing works did. RL-Lock combines structured action chunking with MCTS-guided policy-value learning to efficiently navigate the large combinatorial search space for interlocking assembly generation. We demonstrate through experiments that RL-Lock allows effective generation of interlocking assemblies, especially for challenging cases in which existing approaches take too long or even fail to find a valid solution.

Real-time co-speech gesture generation must produce 3D motion clip by clip as speech arrives. Existing streaming methods are open-loop: each clip depends on past context, but the model cannot check or correct its trajectory. Small errors therefore accumulate and cause drift over long sequences. We observe that this failure is mainly caused by the lack of a forward constraint rather than poor short-clip quality. A plausible key pose at the end of each clip provides a destination anchor that limits drift. Based on this observation, we propose StreamTalk, a closed-loop framework with a periodic generate-retrieve-refine cycle. Streaming Pose-Guided Generation first predicts a coarse clip, retrieves a plausible tail pose from a speaker-specific motion database, and refines the clip using this pose before continuing to the next window. During training, Stochastic Anchor Masking randomly masks pose and translation frames, teaching the model to recover complete motion from sparse boundary conditions. A part-aware DiT separates hand, body, and translation streams to reduce interference between global displacement and local articulation. On BEAT2, StreamTalk achieves state-of-the-art FGD, reduces long-horizon drift relative to open-loop baselines, and runs in real time at 76 FPS. Project page: https://xiangyue-zhang.github.io/StreamTalk/.

Generating expressive 3D talking heads solely from speech remains a significant challenge due to the scarcity of high-fidelity 3D data, which limits the modeling of complex emotional motion patterns. In this paper, we introduce Expressive Talking Head (ETHead), a method for generating 3D facial and head motions that vividly align with the emotional content of input speech. To overcome the data limitations, we design a self-distillation framework that leverages large-scale 2D talking videos to pre-train a specialized speech encoder. By incorporating a novel emotion-modulated probabilistic masking mechanism, this framework aligns speech representations with expressive visual dynamics, allowing the encoder to extract features highly correlated with facial and head motions directly from audio. These features are then leveraged to guide 3D generation, enriching input cues and providing explicit supervision through a joint speech-motion latent space. Extensive experiments demonstrate that ETHead substantially outperforms state-of-the-art methods. Furthermore, our motion-aligned speech encoder can serve as a transferable module, offering a general solution for enhancing expressiveness in other 3D talking head animation frameworks. The project page is available at https://verdure-oss.github.io/ETHead.github.io/.