Peer Revenue Returns subject to peer review

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision

Sunday 28 June

Computer Vision

Can Machines Really See Objects in Images? A Study Based on Syntactic Distance and Visual Self-Referential Instances

Xingyu Peng, Junran Wu, Yue Hou et al. (+9 more)

Can a vision model truly see an object, or does it only fit surface-level visual cues? Following Wittgenstein's view that the limits of language are the limits of the world, we view a model's recognition ability as bounded by the descriptive system it has learned. In current vision models, this system is often realized through learned feature representations that exploit local statistical cues. We therefore ask whether a model can still classify correctly when such local cues provide no stable basis for distinction. We formalize this question with syntactic distance, which measures class separability through the symmetry of the operations mapping one class to the other: positive distance exposes exploitable local features, whereas zero distance requires global semantics rather than local rules. We construct a visual self-referential task in maximum-variance binary noise: positive samples contain a closed square, while negative samples contain an otherwise identical square with one flipped boundary pixel. The two classes differ in global semantics but have zero syntactic distance, making local statistical shortcuts unreliable. Experiments on ResNets and Vision Transformers reveal a consistent phase-transition phenomenon, with accuracy collapsing to random guessing once the image scale crosses a critical point and does not recover within the tested range. Larger training sets and models only delay this collapse, while globally attentive ViTs reach it earlier. These results reveal a structural capability boundary of current architectures on global-concept tasks, suggesting that general intelligence may require creating new language, not reusing an existing one.
Read the full abstract

All authors Xingyu Peng, Junran Wu, Yue Hou, Zhongliang Qiao, Jiaheng Liu, Shangzhe Li, Jichang Zhao, Wenjun Wu, Xianglong Liu, Yongxin Tong, Li Dong, Ke Xu

Computer Vision

FiRe: Frequency Reparameterization as a Preconditioner for Periodic Implicit Neural Representations

Harinandan Shukla, Rajarshi Verma and Jitin Singla

Periodic Implicit Neural Representations (INRs) such as SIREN and FINER assign every neuron, the same global frequency, spending the representational budget inefficiently when local signal content varies. We introduce FiRe (Frequency Reparameterization), that accelerates optimization by reparameterizing per-neuron frequency of periodic INRs without changing their underlying activation function. FiRe gives each neuron a bounded, input-dependent frequency via a separate low-rank gating path and is applicable to any periodic activation function. The gate acts as an implicit preconditioner that improves optimization conditioning at initialization via the Neural Tangent Kernel (NTK). This better-conditioned initialization makes optimization converge faster, and the high-frequency content of the reconstruction tracks the target more closely at a fixed computational budget. On 2D image fitting, FiRe increases PSNR over a parameter-matched baseline (up to +1 dB at short training budgets), with gains that vary with resolution and diminish at full convergence. We characterize how performance depends on resolution, rank, and training budget, and give an NTK account that predicts these trends.
Read the full abstract

Computer Vision

Adaptive Densification for High-Fidelity and Efficient Sparse Gaussian Splatting in Arbitrary-Scale Super-Resolution

Giulio Federico, Giuseppe Amato, Claudio Gennaro et al. (+2 more)

Arbitrary-Scale Super-Resolution (ASR) aims to reconstruct high-resolution images at any continuous magnification. While 2D Gaussian Splatting (GS) has recently shown great promise for ASR, current methods struggle to balance visual quality and computational cost. Approaches targeting high fidelity rely on powerful backbones and uniform, highly dense Gaussian grids, leading to prohibitive memory and inference costs. Conversely, methods prioritizing efficiency aggressively simplify their architectures, severely compromising visual quality. To bridge this gap, we observe that a core capability of GS remains largely underexplored in ASR: the potential for dynamic densification, i.e., the spatially adaptive allocation of Gaussians based on image content. Unlike standard scene fitting, where densification is guided by a known ground truth, applying this to ASR is highly non-trivial because the high-resolution target is exactly what the model must predict. To address this challenge, we propose QuADA-GS, an approach that retains a powerful representational backbone but autonomously predicts where to allocate Gaussians relying strictly on the low-resolution input. By adopting a sparse approach, QuADA-GS refines features and increases Gaussian density strictly where structural complexity demands it. Because this adaptive allocation produces a non-uniform hierarchical topology, we introduce a novel, highly efficient communication mechanism to process these sparse features, bypassing standard dense bottlenecks. Extensive experiments indicate that our approach successfully balances visual quality and computational requirements, providing an improved and competitive trade-off for ASR.
Read the full abstract

All authors Giulio Federico, Giuseppe Amato, Claudio Gennaro, Fabio Carrara, Marco Di Benedetto

Computer Vision

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

Cheng Wan, Yongsen Mao, Wenzheng Wu et al. (+7 more)

Recently, Large Language Models (LLMs) have emerged as promising layout agents for 3D scene generation. Existing layout agents still suffer from implausible layout generation because most of them convert 3D assets and 3D layouts into textual descriptions as inputs and outputs, which involves severe information loss due to the modality gap between texts and 3D assets and 3D layouts. We propose NaLA, a native 3D LLM layout Agent for high-quality 3D scene generation by placing 3D assets in the scene. For the inputs, NaLA encodes 3D scene boundaries and 3D assets directly into the LLM, preserving fine-grained geometry and enabling explicit reasoning over relationships like collisions, surface supporting, and containment. To accurately output the positions and orientations of assets, NaLA adopts a coarse-to-fine prediction mechanism that first predicts discrete poses in an autoregressive manner and then refines the discrete poses with a continuous regression. Trained on diverse layout datasets, NaLA attains strong geometric perception and layout coherence. Experiments demonstrate that NaLA outperforms prior layout agents in both generation quality and inference efficiency, with comprehensive ablation studies to verify each component's effectiveness.
Read the full abstract

All authors Cheng Wan, Yongsen Mao, Wenzheng Wu, Yuxuan Xie, Chucheng Xiang, Runze Wang, Xiang Zhang, Zhongyuan Liu, Rushi Dai, Yuan Liu

Computer Vision

Event-VLA: Action-Conditioned Event Fusion for Robust Vision-Language-Action Model

Jiaxin Liu, Xun Xu, Zhenhao Zhang et al. (+5 more)

Vision-Language-Action (VLA) models have become an important paradigm of embodied AI. However, existing VLA models typically assume well-lit and stable indoor settings, while real-world embodied manipulation may involve degraded RGB observations caused by illumination shifts, posing critical challenges for robust robotic manipulation. To address this gap, we propose Event-VLA, an event-enhanced VLA framework for generalizable manipulation across varying illumination conditions. We formulate VLA-based manipulation under degraded visibility as a practical robustness problem for RGB-centric policies, and introduce event streams as an illumination-robust, motion-sensitive complementary observation to improve robustness across visibility levels. Specifically, unlike conventional multimodal fusion that directly merges event features into the global semantic token space, Event-VLA injects event information through an action-query routing pathway. It uses learnable action queries to extract task-relevant semantics from the VLA reasoning process, and selectively aggregates event tokens via gated cross-attention to construct event-aware action representations. This design preserves the pretrained RGB-language semantic priors while effectively leveraging event information for robust action prediction. Experiments in simulation and real-world deployment show that Event-VLA maintains strong manipulation performance under normal lighting and improves success rates under low-light degradation and near-dark real-world settings.
Read the full abstract

All authors Jiaxin Liu, Xun Xu, Zhenhao Zhang, Hanqing Wang, Ruiqi Chen, Shi Chang, Weiyu Guo, Laurent Kneip

Computer Vision

DR-GS: Physically-Based Deformable and Relightable 2D Gaussians

Jiaxin Li, Tong Wu, Yi Wei et al. (+2 more)

Gaussian splatting (GS) has garnered significant attention in VR/AR and digital content creation due to its explicit parameterization and efficient rendering capabilities. However, existing GS-based methods for deformable objects face two key limitations: (i) illumination is erroneously baked into textures, causing physically inconsistent responses under dynamic deformations and lighting changes; (ii) snapshot-based reconstruction restricts post-reconstruction material editing. To address these challenges, we propose Deformable and Relightable GS (DR-GS), a unified Gaussian framework that integrates physically-based inverse rendering, relighting, and deformation-aware manipulation. Through explicitly disentangling geometry, illumination, and material representations, DR-GS overcomes the limitations of static snapshots, resolving unrealistic appearance under varying conditions while enabling post-reconstruction parameter editing. Extensive experiments show that DR-GS achieves leading visual quality across static reconstruction, dynamic deformation, and relighting, reliably preserving reflections and specular highlights on glossy surfaces. It further establishes a fully decoupled geometry-illumination-material pipeline, enabling high-quality 3D asset creation and comprehensive post-editing.
Read the full abstract

All authors Jiaxin Li, Tong Wu, Yi Wei, Tailin Wu, Li Zhang

Computer Vision

SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring

Yufei Zhang, Chenlu Zhan, Gaoang Wang et al. (+1 more)

Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches. Directly optimizing against these unreliable 2D targets forces the 3D representation to absorb multi-view contradictions, leading to severe error accumulation. To resolve this limitation, we propose SAD-GS, a framework for learning reliable 3D semantic Gaussian fields via dynamic geo-semantic anchoring. Specifically, Semantic Anchor Distillation (SAD) distills per-view visual embeddings into consensus text anchors to establish a viewpoint-invariant semantic identity. Concurrently, the Geo-Semantic Feedback Loop (GSFL) leverages the evolving 3D field to actively filter tracker anomalies and refine spatial mask assignments via a conservative three-gate update rule. Extensive evaluations on LERF-OVS, 3D-OVS, and Mip-NeRF360 show that SAD-GS consistently achieves the best overall performance in both open-vocabulary localization and semantic segmentation. These comprehensive improvements validate the effectiveness and robustness of dynamic geo-semantic anchoring for reliable 3D semantic Gaussian field learning.
Read the full abstract

All authors Yufei Zhang, Chenlu Zhan, Gaoang Wang, Hongwei Wang

Computer Vision

L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction

Zetian Song, Chenming Wu, Junnan Liu et al. (+6 more)

High-fidelity reconstruction of dynamic urban environments is a cornerstone of autonomous driving simulation and large-scale world modeling. While 3D Gaussian Splatting (3DGS) has established a new standard for real-time rendering, its reliance on expensive per-scene optimization limits scalability. Conversely, recent feedforward methods that infer Gaussian parameters offer faster speed but face fundamental bottlenecks: they are memory-prohibitive at high resolutions and struggle to fuse dense multi-view observations consistently. This paper presents L2D2-GS, a unified framework that reformulates generalizable reconstruction not as a one-shot regression, but as a robust iterative process of optimization and densification. To resolve the ambiguity of supervision in primitive generation, we propose a self-supervised densification policy that derives explicit reward signals from global reconstruction gains to guide local densification. Furthermore, we mitigate irreversible early-stage artifacts through a geometric regularization mechanism, utilizing reparameterization to constrain the optimization manifold and prevent convergence to poor local optima. Extensive experiments on the PandaSet and Waymo datasets demonstrate that our method achieves state-of-the-art reconstruction fidelity and strong zero-shot generalization, while using fewer primitives than competing baselines.
Read the full abstract

All authors Zetian Song, Chenming Wu, Junnan Liu, Chitian Sun, Liangliang He, Hangjun Ye, Jiaqi Zhang, Siwei Ma, Wen Gao

Computer Vision

SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers

Xuanhua Yin, Yuxuan Jia, Chuanzhi Xu et al. (+1 more)

High-resolution Diffusion Transformer (DiT) inference contains substantial spatial redundancy, but many spatially adaptive implementations encode regional computation as attention masks, which can inadvertently move scaled dot-product attention (SDPA) away from FlashAttention fast paths. We identify this avoidable systems bottleneck as Mask-Induced Dispatch Tax (MIDT) and show that it grows with latent sequence length. We introduce SAFE-DiT, a training-free Semantics-Aware Fast-path Execution framework that separates exact mask elision from approximation-based spatial scheduling. SAFE-DiT removes only provenance-certified image self-attention masks that induce a row-wise constant shift in attention logits, preserves semantics-bearing masks such as text-padding masks, and realizes spatial adaptation through prompt-conditioned token partitioning, selective state updates with global context, and periodic context refresh. We call this acceleration-only configuration SAFE-Core and report sensitivity-weighted classifier-free guidance separately as SAFE-DiT+SW. On the evaluated PyTorch SDPA stack, redundant masks make long-sequence attention $4.1\times$ to $5.8\times$ slower than the mask-free path. On Lumina-Next, SAFE-DiT achieves $2.69\times$ end-to-end acceleration at $1024^2$ resolution and $5.09\times$ at $2560^2$, reduces peak memory at $2560^2$ from 94.1 to 27.9 GB, and enables $3072^2$ generation when dense inference runs out of memory. Paired metrics, component ablations, and a blinded human study support visual non-inferiority of SAFE-Core to the dense fast-path baseline, while SAFE-DiT+SW provides a separate prompt-alignment operating point without reintroducing spatial self-attention masks. Code is available at https://github.com/xuanhuayin/SAFE-DiT.
Read the full abstract

All authors Xuanhua Yin, Yuxuan Jia, Chuanzhi Xu, Weidong Cai

Computer Vision

Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking

Xiao Wang, Liye Jin, Dan Xu et al. (+5 more)

Vision-language tracking guided by natural language specifications leverages high-level semantic cues of target objects to substantially boost tracking accuracy and robustness. Existing studies have verified that adaptively optimizing textual descriptions throughout the tracking process can effectively mitigate the semantic-visual mismatch induced by dynamic variations in target appearance, position, and other inherent attributes. Nevertheless, mainstream methods that directly generate textual information via sequence models or large language models inevitably suffer from inherent defects, including erroneous target updating, excessive background distraction, and pervasive hallucination artifacts. To address the aforementioned limitations, this paper proposes a novel language dependency parsing mechanism to precisely distill core tracking principal components, encompassing target objects, semantic concepts, and background contextual information. On this basis, we perform component-aware adaptive textual description updates by exploiting the powerful cross-modal understanding capability of the pre-trained vision-language model Qwen-VL. By integrating the proposed elaborately designed modules into the baseline framework, our method achieves consistent and superior tracking performance on multiple large-scale vision-language tracking benchmarks, including TNL2K, LaSOT, TNLLT, and OTB-LANG. The source code and pre-trained models will be released at https://github.com/Event-AHU/Open_VLTrack.
Read the full abstract

All authors Xiao Wang, Liye Jin, Dan Xu, Yuehang Li, Lan Chen, Yaowei Wang, Yonghong Tian, Jin Tang

Computer Vision

Fast Enough to Act: Spatio-Temporal Visual Token Merging for Low-Latency Robotic VLMs and VLAs

Junzhou Chen, Jindong Wang and Gang Zhou

Vision-language models and vision-language action models endow the robot with unprecedented capabilities. However, the input of video and high-resolution images yields a massive number of visual tokens, leading to extremely high inference latency and severely hindering the robot's real-time control. To break through this computational bottleneck, we propose ST-Merge, a plug-and-play, training-free framework that efficiently fuses redundant tokens directly during the visual encoding phase. By explicitly constructing 3D spatiotemporal coordinates, it employs a multi-queue parallel matching and weighted aggregation mechanism to achieve efficient and geometrically consistent fusion of redundant tokens across frames. In addition, we introduce a post-merge positional correction mechanism that effectively eliminates spatial deviation caused by merging by dynamically re-evaluating the rotational position code of the weighted centroid of the vision token, thereby ensuring the high-precision spatial awareness required for dexterous operation. In the Video Question Answering task on the mainstream VLM, Qwen2.5-VL, ST-Merge achieves a 2$\times$ inference speedup with only a tiny 1% loss in precision. When deployed on the $\pi_{0.5}$ VLA policy, ST-Merge achieves an 8.3$\times$ speedup at 1024 $\times$ 1024 resolution and matches the baseline success rate at this high-resolution setting. At lower resolutions, it introduces a small drop in accuracy.
Read the full abstract

Computer Vision

W4A4 Quantization for Inference on Wan2.2-I2V-A14B

Yidong Chen, Chengyu Shi and Jiahao Liu

We summarize our submission to Sub-Challenge 1: W4A4 Quantization for Inference (HiF4 / MXFP4) of the ICME 2026 Low-Bit-width Large-Model Quantization Challenge. The sub-challenge targets 4-bit weight and 4-bit activation inference on Wan-AI/Wan2.2-I2V-A14B under HiF4 or MXFP4 numerical formats. We adapt two complementary ideas from LLM quantization, MixQ-style mixed precision for sparse activation outliers and SmoothQuant-style per-channel smoothing, together with block-wise HiF4 packing for Wan2.2 feed-forward linear layers. Calibration on representative OpenS2V-5M batches identifies heavy-tailed activation channels; smoothing rebalances dynamic range before W4A4 rounding; and a dual-branch GEMM preserves outlier columns in higher precision while the bulk of channels use strict W4A4. On official VBench I2V metrics, our pipeline stays within 2-3.5 percent of FP16 on most quality axes and improves motion smoothness, outperforming a native HiFloat4 baseline that degrades roughly 5 percent relative to FP16 across all reported scores.
Read the full abstract

Computer Vision

Multi-scale Object-Aware Gaze Estimation via Geometric Reasoning

Jiajie Mi, Xinyu Liu, Mengke Song et al. (+1 more)

Gaze target estimation aims to predict the semantic object an observer fixates upon within an image, a task deeply rooted in the object-oriented nature of human gaze. Observers tend to select a specific semantic entity as the attentional target, rather than responding randomly across arbitrary regions of the image. However, existing methods typically model this task as a direct mapping from global features to gaze heatmaps, essentially treating it as a pixel-level regression problem. This approach fails to explicitly represent the gazed object as a distinct entity, making it difficult to produce stable and semantically consistent predictions in complex scenes. To address this, we propose a two-stage gaze estimation framework guided by object semantics, reformulating gaze target estimation as a hierarchical reasoning process. Our method incorporates object-level representations during feature encoding to align image features with discrete semantic entities, then introduces multi-scale feature fusion and geometric constraints from head pose and gaze direction for fine-grained localization and object-level discrimination. Extensive experiments on GazeFollow, VideoAttentionTarget, ChildPlay, and GOO-Real demonstrate that our method achieves AUC of 0.961, 0.948, 0.987, and 0.977 respectively, delivering strong performance across all benchmarks while maintaining a compact parameter size of 7.1M.
Read the full abstract

All authors Jiajie Mi, Xinyu Liu, Mengke Song, Chenglizhao Chen

Computer Vision

HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video

Yiming Jiang, Hanzhang Tu, Wenfeng Song et al. (+5 more)

Uncalibrated volumetric video streaming for human reconstruction is essential for holographic communication and AR/VR, yet remains challenging due to the need for temporal consistency and computational efficiency from sparse-view inputs. Existing methods rely on per-scene optimization or calibrated cameras, while recent feed-forward models are limited to low-resolution (0.5K) single-frame synthesis. We present HiReFF, a feed-forward method for 2K-resolution 360{\deg} human video reconstruction from uncalibrated sparse-view videos. Our framework decomposes the problem into two key tasks: foreground 3D Gaussian reconstruction from sparse-view videos (four views separated by 90{\deg}) and computationally efficient high-resolution synthesis. To enable the former, we propose Scale-synchronized Camera Calibration to resolve scale ambiguity for multi-view supervision, and Gaussian-wise Foreground Masking to reconstruct clean foregrounds by modulating Gaussian parameters. For efficient high-resolution synthesis, our High-resolution Side-tuning achieves 2K rendering by augmenting the Gaussian head with supplementary features while keeping the backbone at 0.5K, drastically reducing computational overhead. Experiments demonstrate that HiReFF significantly outperforms existing methods in high-resolution streaming volumetric video reconstruction. https://iridescentjiang.github.io/HiReFF
Read the full abstract

All authors Yiming Jiang, Hanzhang Tu, Wenfeng Song, Siyou Lin, Liang An, Shuai Li, Aimin Hao, Yebin Liu

Computer Vision

RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction

Aymen Mir, Riza Alp Guler, Jian Wang et al. (+3 more)

We study the problem of physically plausible shadow casting when animating 3D Gaussian Splatting (3DGS) avatars, either individually or in multi-avatar and object-interaction scenarios, within existing 3DGS scenes. In contrast to prior methods that rely on binary hit tests and mesh-based shadow casters, our method performs shadow computation entirely in Gaussian space, without requiring any mesh reconstruction. We introduce RAGA, a Ray-Traced Gaussian Shadow Casting formulation based on exact ray-Gaussian line integrals. For each occluding Gaussian, we integrate the opacity profile along the shadow ray and normalize by the theoretical maximum integral, producing a weight that captures how the ray traverses the occluder rather than merely whether an intersection occurred. To reduce temporal variance from clothing deformations in animated avatars, we further introduce an avatar proxy representation that stabilizes shadow casting while preserving visual fidelity. We implement RAGA using custom CUDA kernels integrated with the NVIDIA OptiX framework; as such, our shadow tracer runs at rates of about 50 FPS. We evaluate on single-avatar, multi-avatar, and avatar-object interaction scenarios across multiple datasets, demonstrating substantially improved shadow realism, temporal stability, and scene coherence. Our project page is available at https://miraymen.github.io/raga/.
Read the full abstract

All authors Aymen Mir, Riza Alp Guler, Jian Wang, Peter Wonka, Bing Zhou, Gerard Pons-Moll

Computer Vision

FDM-MFVT: Few-step Sampling Diffusion Model for Mask-Free Virtual Try-On

Jiaxin Liu, Xiaoye Liang, Lai Jiang et al. (+2 more)

Image-based Virtual Try-On (IVTON) has greatly advanced through diffusion models, yet existing methods require many sampling steps and depend on masks with costly auxiliary networks. In addition, the absence of large-scale mask-free paired datasets further limits the development of mask-free IVTON. We propose FDM-MFVT, a few-step diffusion model for mask-free IVTON, integrating an Outfit-aware Noise Optimization Module (OANO) and an Instruction-driven Try-on Module (IDT) to enhance efficiency and flexibility.The OANO module initializes the alignment space with noise using the input image and only needs 6 steps to generate a higher-fidelity try-on image compared to 30 steps.The IDT module uses virtual try-on prompts and efficient adaptation to generate high-quality results from garment and person images alone. We further introduce MFVT, a 30,000-pair mask-free IVTON dataset. Experiments show that FDM-MFVT achieves superior quantitative and qualitative results with fewer inference steps than mask-based and mask-free baseline methods.
Read the full abstract

All authors Jiaxin Liu, Xiaoye Liang, Lai Jiang, Mai Xu, Jun Liu

Computer Vision

D$^{2}$R$^{2}$OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution

Hongyu An, Xinfeng Zhang, Xu Fan et al. (+3 more)

With the growing demand for immersive visual experiences, high-quality omnidirectional images (ODIs) have become increasingly important. However, limitations in imaging devices and transmission bandwidth often lead to low-resolution ODIs, hindering the rendering of fine-grained 360{\deg} details, especially in the presence of real-world degradations and geometric distortions. Existing real-world super-resolution (Real-SR) methods are inadequate for ODIs, as their degradation models fail to account for the complex imaging pipeline involving fisheye capture and Equirectangular Projection (ERP), introducing severe aliasing and projection-specific distortions. To address these challenges, we propose D$^{2}$R$^{2}$OSR, a Degradation-Disentangled Representation framework for Real-world Omnidirectional image Super-Resolution. D$^{2}$R$^{2}$OSR explicitly models degradations arising from both fisheye imaging and ERP projection, guided by two key insights: (1) projection priors play a critical role in shaping real-world degradations, and (2) human perception in immersive environments is inherently viewpoint-centric. Accordingly, we introduce a Perspective Projection Representation (PPR) operating alongside the ERP branch to capture viewpoint-aware features, together with a Degradation-Specific Module (DSM) that jointly models ERP-induced geometric distortions and PPR-specific real-world degradations. Extensive experiments demonstrate that D$^{2}$R$^{2}$OSR achieves state-of-the-art performance and produces visually compelling, high-fidelity omnidirectional Real-SR results while maintaining favorable computational efficiency for low-resource deployment.
Read the full abstract

All authors Hongyu An, Xinfeng Zhang, Xu Fan, Shijie Zhao, Li Zhang, Ruiqin Xiong

Computer Vision

MirrorPPR: Exemplar-Based Portrait Photo Retouching

Zhihong Liu, Zheng Li, Jiachun Jin et al. (+4 more)

While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. Textual descriptions struggle to convey fine-grained changes to facial features and body proportions. To address this gap, we introduce Exemplar-Based Portrait Photo Retouching, where the model is given an exemplar pair and tasked with inferring and applying the same retouching operations to a new query image. Existing exemplar-based editing methods primarily focus on tasks with pronounced visual transformations. In contrast, structural portrait retouching involves extremely delicate and localized modifications, making accurate extraction and transfer of these edits challenging. To tackle this, we propose MirrorPPR, a novel framework designed to capture and transfer subtle structural retouching operations. Our method uses a Retouching Operation Extractor to capture the subtle differences from the exemplar pair. The extracted representations are then injected into a pre-trained Diffusion Transformer (DiT) through a connector and Low-Rank Adaptation (LoRA) modules. Furthermore, constructing perfectly aligned cross-identity training pairs is severely hindered by operation misalignment. To overcome this, we propose an advanced data self-augmentation paradigm that ensures strictly aligned retouching operations. To alleviate data scarcity and support this novel task, we introduce MirrorPPR47M, a large-scale dataset with over 47 million retouched pairs. By structuring the dataset into simulated and professional subsets, we enable progressive curriculum learning to smoothly optimize the network. Extensive experiments demonstrate that MirrorPPR significantly outperforms existing baselines in both retouching quality and identity preservation. The project page is available at https://sjtu-deng-lab.github.io/MirrorPPR.
Read the full abstract

All authors Zhihong Liu, Zheng Li, Jiachun Jin, Siqi Kou, Yitao Jian, Fengpei Yu, Zhijie Deng

Computer Vision

Occlusion-Robust Multi-Object Decoupling for Physics-Based Robotic Interaction

Xin Dong, Lihan Zhang, Tianru Dai et al. (+2 more)

We propose a mask-free method for lossless multi-object 3D reconstruction from sparse and occluded real-world views, enabling physically plausible robotic interaction via Material Point Method (MPM) simulation. Our key insight is that object coupling stems from occlusion and limited viewpoints, which we address by formulating multi-object decoupling as a sparse-view reconstruction problem. Using 3D Gaussian Splatting as base representation, we first obtain coarse instance partitions with a SAM2-trained segmentation field. Rather than relying on masks, we reconstruct fragmented geometries by leveraging a joint Score Distillation Sampling (SDS) process, which integrates reference-view supervision with novel-view synthesis guided by 2D and 3D diffusion priors to enforce both texture fidelity and 3D consistency. Furthermore, we incorporate geometry-aware priors such as intra-object and inter-object similarity to regularize geometric reasoning. Experimental results demonstrate that our method produces complete, simulation-ready 3D objects without requiring manual masks, enabling realistic dynamic interactions on both synthetic, robotic and real-world datasets.
Read the full abstract

All authors Xin Dong, Lihan Zhang, Tianru Dai, Wenfeng Deng, Yansong Tang

Computer Vision

Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision

Dacheng Qi, Chenyu Wang, Jingwei Xu et al. (+2 more)

Computer-aided design (CAD) plays a fundamental role in modern manufacturing by providing the high precision required for industrial production. Recent large language model based approaches formulate CAD generation as a sequence prediction problem and have achieved promising results. However, existing methods and evaluation protocols primarily emphasize visual similarity, while overlooking precise geometric parameters and correct metric scale. Small numerical deviations that are negligible at the shape-level may still violate industrial tolerance requirements, a problem further compounded by current autoregressive paradigms that utilize command sequence representations, aggressively quantize numerical parameters to ease LLM prediction. In this work, we present Pointer-CAD v2. Compared with v1 (arXiv:2603.04337), this version directly predicts continuous values, bypassing the need for quantized numerical parameters and thereby eliminating quantization errors. Specifically, we propose a unified framework that decouples parameter reasoning from geometric construction through a Plan-Then-Construct paradigm. Our method first produces a structured design plan with explicit metric scale parameters. These parameters are organized into a dictionary and directly referenced during sequence generation via a pointer mechanism, eliminating discretization errors and ensuring dimensionally consistent execution. In addition, we construct a new large-scale dataset with plan-level annotation and introduce three hierarchical geometry accuracy metrics to evaluate parametric fidelity at the vertex, edge, and face levels. Extensive experiments demonstrate that Pointer-CAD v2 consistently outperforms existing baselines and achieves substantial improvements in geometric accuracy, enabling reliable CAD generation for precision-critical engineering applications.
Read the full abstract

All authors Dacheng Qi, Chenyu Wang, Jingwei Xu, Yi Ma, Shenghua Gao

Computer Vision · Cross-listed from cs.LG

Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment

Chen Wang, Peiran Yun, Pan Xie et al. (+1 more)

Diffusion and continuous-flow generative models achieve high-quality generation, and their deterministic sampling can be formulated as solving learned ODE dynamics. However, accurate ODE discretization often requires many steps, making efficient few-step generation a key challenge. Among acceleration strategies, reflow-based distillation simplifies teacher ODE trajectories so that a student model can approximate the teacher transport with fewer steps. We identify a theoretical limitation of this paradigm, namely that trajectory matching can under-determine the distribution induced by the student model. In particular, two student models can attain the same trajectory-matching loss while inducing different endpoint marginal distributions, which may lead to different generation quality. To address this limitation, we introduce a marginal-alignment regularizer that penalizes the discrepancy between the student-induced marginal and the corresponding teacher marginal at the endpoint of each distillation interval. The regularizer is computed by tracking log-density changes along the ODE induced by the student model and evaluating scores from the frozen teacher model, without requiring auxiliary trainable networks or adversarial optimization. The resulting framework applies uniformly to the reflow family, including vanilla reflow and piecewise reflow. We further prove a telescoping total-variation bound showing that local marginal alignment controls the final-time discrepancy between the student-induced and teacher-induced distributions. Experiments on benchmark backbones demonstrate the effectiveness of the proposed method for few-step generation.
Read the full abstract

All authors Chen Wang, Peiran Yun, Pan Xie, Ke Deng

Computer Vision

ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving

Dingyi Yao, Xinqi Zhang, Lihui Peng et al. (+3 more)

Synthetic data mitigates the data scarcity problem in autonomous driving perception. However, the synthetic-to-real gap leads to performance degradation, hindering real-world model generalization. Although current methods leverage diffusion models for photorealistic style transfer to bridge this gap, they critically ignore a practical asymmetry: while synthetic data possesses perfect pixel-level annotations, real-world style reference images generally lack corresponding labels. Consequently, existing methods relying on symmetric semantic guidance suffer from either prohibitive annotation costs or severe semantic misalignment. To address this dilemma, we formally propose a novel task: Asymmetric Style Transfer for Autonomous Driving (ASTAD), which requires semantically consistent transfer using only labeled synthetic content and unlabeled real-world references. We further introduce the ASTModel, a training-free two-stage framework designed to bridge this domain gap under asymmetric constraints. ASTModel first extracts a coarse semantic prior from the unlabeled target, followed by dynamic prior refinement and class-consistent style injection during the denoising process. Extensive experiments demonstrate that ASTModel significantly outperforms existing methods in downstream perception utility and structural fidelity, while offering a 3.2$\times$ inference speedup. This work aligns synthetic-to-real adaptation with practical constraints, holding the potential to accelerate the scalable deployment of robust autonomous driving systems. Code: https://github.com/Dingyi-Yao/ASTAD.
Read the full abstract

All authors Dingyi Yao, Xinqi Zhang, Lihui Peng, Jianming Hu, Danya Yao, Yi Zhang

Computer Vision

ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation

Cong Wang, Haiyu Wu, Zhiwei Jiang et al. (+4 more)

Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR) image generation has recently emerged as a new generative paradigm characterized by next-scale prediction, for which concept erasure remains largely unexplored. In this paradigm, semantic information is highly compressed at early scales, leading to severe entanglement between unsafe and unrelated semantics. In this paper, we propose ScaleErasure, an inference-time concept erasure method that performs minimal intervention. ScaleErasure precisely selects and guides predicted logits that are most relevant to the unsafe concept, thereby enabling effective erasure under severe semantic entanglement. Specifically, ScaleErasure performs two additional forward passes conditioned on the unsafe concept and the corresponding safe concept, and leverages their outputs to guide the target logits away from unsafe concepts toward safe concepts. To enable precise and minimal intervention, logits selection and guidance are conducted across three dimensions: scales, tokens, and bit channels. Experiments demonstrate that ScaleErasure outperforms adapted baselines in the next-scale AR paradigm, achieving more precise concept erasure while largely preserving general generative capability. The code is available at https://github.com/coziiizz/ScaleErasure.
Read the full abstract

All authors Cong Wang, Haiyu Wu, Zhiwei Jiang, Zifeng Cheng, Fei Shen, Yafeng Yin, Qing Gu

Computer Vision

Enhancing Part-Level Point Grounding for Any Open-Source MLLMs

Jin-Cheng Jhang, Fu-En Wang, Xin Yang et al. (+4 more)

Visual grounding aims to associate free-form textual queries with specific regions in an image. While recent Multimodal Large Language Models (MLLMs) have demonstrated promising capabilities in this domain, they primarily excel at object-level grounding and often struggle with part-level grounding-an essential requirement for fine-grained tasks such as robotic manipulation. In this work, we introduce a general approach that equips any open-source MLLMs with accurate 2D part-level point grounding, offering a more direct alternative to conventional grounding representations. Our method leverages the attention mechanisms inherently present in MLLMs. By synthesizing text-conditioned, grounding-aware queries within intermediate layers via the proposed Q-Synth Module, we capture target-relevant attention patterns and refine them with a lightweight Attention-to-Point Decoder, which converts these patterns into a point-centric heatmap for final prediction. Notably, all original MLLM parameters are frozen, ensuring full preservation of their pre-trained capabilities. Experiments show that our design consistently improves part-level grounding accuracy across datasets and can be seamlessly integrated into any open-source MLLMs.
Read the full abstract

All authors Jin-Cheng Jhang, Fu-En Wang, Xin Yang, Nan Qiao, Lu Xia, Min Sun, Cheng-Hao Kuo

Computer Vision · Cross-listed from cs.LG

Nonlinear mixture model motivated subspace clustering

Ivica Kopriva

We derive the linear union-of-subspaces (UoS) model for subspace clustering (SC) from the nonlinear mixture model (NMM) used in blind source separation (BSS) to represent a D-dimensional observation vector as an unknown multivariate nonlinear mapping of C latent variables. Assuming the mapping is differentiable up to an unknown order K, we approximate NMM by a K-th order Taylor expansion, yielding a model equivalent to the linear UoS framework underlying SC. This establishes that: (i) the smoothness order K corresponds to the unknown subspace dimension d; (ii) KC equals the number of anchors; and (iii) the sparsity of the representation vector equals K (i.e., d). These relationships enable estimation of bounds on subspace dimension, and that is validated on six benchmark datasets using five established SC algorithms. Established theoretical results are important for post-processing of self-representation matrices estimated by SC algorithms.
Read the full abstract

Computer Vision

Confidence-feedback-weighted graph matching network: online-offline laser-induced damage site matching under complex interference

Yueyue Han, Guanhua Chen, Hangcheng Dong et al. (+6 more)

Online inspection images of final optics in high-power laser facilities contain pseudo-damage sites that closely resemble true damage sites. Determining the authenticity of online-detected sites is therefore difficult and requires accurate matching to offline ground-truth sites. However, this matching remains highly challenging due to limited match-discriminative features, local geometric distortions, and numerous distractor sites. Existing matching models mainly suppress distractors implicitly through loss-function supervision. We propose a confidence-feedback-weighted graph matching network that requires only damage-site centroid coordinates as input. It estimates node matchability confidence from each round of matching scores and feeds it back as a reliability weight to guide subsequent edge-feature aggregation, thereby suppressing distractor propagation and enhancing cross-graph discriminability. Within this framework, a geometric consistency constraint calibrates spurious high-confidence matchability estimates, while a hard-example mining loss improves discrimination between structurally similar sites. Experiments on our Complex-Scene dataset show that the proposed method achieves a matching F1-score of 96.36$\%$ with robust and efficient performance.
Read the full abstract

All authors Yueyue Han, Guanhua Chen, Hangcheng Dong, Kang Zhang, Fengdong Chen, Zhitao Peng, Fa Zeng, Qihua Zhu, Guodong Liu

Computer Vision

Synthetic CT as a First Safeguard for Choosing Medical VLMs in Lung Cancer Screening

Fakrul Islam Tushar and Geoffrey D. Rubin

Many medical vision–language models (VLMs) are publicly available, but a site adopting one for a new imaging task rarely has the labeled real data needed to compare them. Because synthetic CT has ground truth by construction, a site could instead rank candidate models on synthetic scans, if the ranking carries over to real data. We study when it does for lung CT, using five public VLMs and three routine screening tasks, namely detecting a nodule, locating its lobe, and estimating its size, on 85,021 synthetic and 26,085 real slices from seven datasets. For nodule presence and size, the synthetic ranking matches the real one with a rank correlation of 0.98. For lobe, the ranking is only moderately preserved, with a rank correlation of 0.80. We also propose TrialCouncil, a training-free method that uses synthetic accuracy to select one model, combine several, or defer uncertain cases. On real CT, it outperforms standard voting methods in every lobe and size setting and outperforms the best synthetic model on lobe, while selecting the best synthetic model works better for presence. Synthetic CT can therefore serve as a first safeguard when choosing a medical VLM without labeled real data.
Read the full abstract

Computer Vision

Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstruction

Shuaikang Zhu, Yiding Sun and Yang Yang

Reconstructing continuous 3D human poses from unconstrained videos is challenging, especially in extreme motion scenarios involving severe motion blur and occlusion. Current state-of-the-art methods typically rely on implicit temporal attention to aggregate features across frames. However, under severe visual degradation, input features often suffer from collapse, rendering them indistinguishable from noise. In such cases, implicit aggregation fails to distinguish valid signals, leading to catastrophic reconstruction errors. To address this robustness gap, we propose a simple yet effective framework called Anchor-guided adaptive inter-frame motion cues propagating (Again-Pose), reformulating pose estimation in degraded frames as a motion-guided recovery task. Instead of blindly smoothing features, we explicitly identify high-quality Anchor Frames based on feature saliency and propagate reliable kinematic cues to "inpaint" the poses of degraded intermediate frames. Specifically, a Dual-path Motion-aware Module captures fine-grained inter-frame dynamics, while a Difference-weighted Fusion Module adaptively propagates these cues to suppress drift. Extensive experiments on standard benchmarks (Human3.6M, 3DPW, PoseTrack) and the challenging FineDiving dataset demonstrate that Again-Pose significantly outperforms state-of-the-art methods in robustness and stability, effectively recovering plausible poses where other methods fail.
Read the full abstract

Computer Vision · Cross-listed from cs.CL

Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study

Aditya Pratap Singh

OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on English and Chinese document benchmarks, yet their behaviour on Indic scripts is largely uncharacterised. We benchmark ten systems on Devanagari (Hindi): classical EasyOCR; open VLMs (Qwen2.5-VL-3B, Qwen3-VL-8B, olmOCR-7B); specialised OCR-VLMs (DeepSeek-OCR, Unlimited-OCR); and frontier closed models (Gemini 2.5 Flash, Claude Opus 4.7, GPT-5.5, Mistral OCR), across four synthetic degradation conditions and 300 real printed scans. We report four findings. First, on clean rendered text all ten cluster within chrF++ 91 to 98, so synthetic text does not separate them. Second, under degradation the specialised OCR-VLMs are the most fragile: DeepSeek-OCR suffers rare but catastrophic repetition failures (outputs up to 71 the reference length) that wreck its corpus mean even though its median is the best of any system, which is why we report median and catastrophic-rate instead of the mean. Third, on real scans nine of the ten systems collapse (EasyOCR falls from chrF++ 93.6 to 58.3) and the field spreads across a 76-point range, so synthetic renders badly overstate Devanagari quality. Fourth, strong English OCR does not predict Indic OCR: GPT-5.5 drops to chrF++ 58.5 (tying classical EasyOCR) and olmOCR-7B, the model behind olmOCR-Bench, falls to 40.5, while the open Qwen3-VL-8B (75.2, runnable on a single 24 GB GPU) beats GPT-5.5 and approaches Mistral; Gemini and Claude lead at 86.3 and 82.2. An error taxonomy separates surface errors (numerals, punctuation) from structural ones (conjuncts, matras, nukta), and a byte-level (ByT5) post-corrector improves a cheap engine on its own error distribution (chrF++ +1.2 to +1.5) but does not transfer across engines. We release the benchmark, code, and models.
Read the full abstract

Computer Vision

Zero-Gated Language-conditioned Human Motion Prediction

Guanhui Qiao, Lu Zhou, Ding Jiang et al. (+1 more)

Pose histories provide the core kinematic evidence for 3D human motion prediction, but they lack explicit high-level semantic guidance. This paper introduces ZGL, a lightweight language-conditioned predictor that uses captions of the observed motion as a semantic prior while preserving a strong motion backbone as the main source of dynamics. We render only the observed poses, generate a one-sentence description with a vision-language model, encode the caption with a frozen CLIP-L text tower, and project it into a small set of conditioning tokens. These tokens are injected into a DCT-based spatial-temporal Transformer by compact crossattention adapters with zero gates: each adapter output is multiplied by a learnable gate initialized to zero, so the full network is numerically identical to the pose-only baseline at initialization and can learn to use language only when it reduces prediction error. On Human3.6M, ZGL improves overall MPJPE over representative motion-prediction baselines in our comparison. Results on CMUMocap further show that compact caption conditioning transfers to a second benchmark and provides a practical semantic cue for 3D human motion prediction.
Read the full abstract

All authors Guanhui Qiao, Lu Zhou, Ding Jiang, Jinqiao Wang