Peer Revenue Impact factor: volatile

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision

Sunday 26 July

Computer Vision

ConFusion: Continuous Fusion Space Learning for Fine-Grained Controllable Infrared and Visible Image Fusion

Guo Yurong, He Yufei, Li Yonghao et al. (+3 more)

Controllable infrared-visible image fusion aims to integrate complementary thermal and structural information with flexible region-aware modulation, producing fused images that adapt to diverse user requirements and downstream tasks. However, existing methods typically rely on predefined discrete control conditions, leading to a sparse space that fails to support fine-grained modulation demands. To address this, we propose ConFusion, a novel framework that learns the continuous fusion space via Gaussian-conditioned spatial-aware modulation, enabling instance-level fine-grained controllable infrared and visible image fusion. ConFusion employs a dual-branch architecture to disentangle modality-invariant and modality-specific representations under joint reconstruction and text-guided semantic alignment. Gaussian-conditioned instance modulation variables coupled with Grounded SAM-based instance masks guide instance-level fine-grained modulation through the Mask-Guided Specific Feature Modulator, while the Text-Driven Invariant Feature Enhancer improves semantic consistency and enhances fusion. During inference, the multimodal large language model parses user intents into instance-level modulation variables to guide image fusion. Extensive experiments show that ConFusion achieves state-of-the-art performance across multiple metrics in both fusion quality and downstream tasks, while supporting fine-grained controllable image fusion. Our code is available at https://github.com/HeyufeiAnto/Confusion
Read the full abstract

All authors Guo Yurong, He Yufei, Li Yonghao, Chang Dongliang, Zhang Ke, Ma Zhanyu

Computer Vision

Weakly Supervised Instance-Level Gleason Pattern Estimation Using Primary and Secondary Labels

Nao Sugeta, Kaito Shiku, Shinnosuke Matsuo et al. (+1 more)

In prostate cancer histopathology, the Gleason Score is determined by the most frequent (Primary) and second most frequent (Secondary) Gleason patterns within a whole-slide image. Although these slide-level labels are routinely available in clinical practice, instance-level Gleason annotations are rarely provided, making patch-level learning challenging. We propose a Multiple Instance Learning (MIL) framework that estimates instance-level Gleason patterns from slide-level Primary and Secondary labels. The proposed method formulates instance-level learning according to the clinical definition of the Gleason Score by aggregating instance predictions into class counts and explicitly modeling the Primary pattern, Secondary pattern, and their dominance. Experimental results demonstrate that the proposed formulation enables effective instance-level learning and outperforms existing MIL approaches on the SICAP-MIL dataset.
Read the full abstract

All authors Nao Sugeta, Kaito Shiku, Shinnosuke Matsuo, Ryoma Bise

Computer Vision

JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents

Yunlong Lin, Zixu Lin, Zhaohu Xing et al. (+23 more)

Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent generative models can synthesize high-quality images, videos, audio clips, UI elements, storyboards, slides, and other creative assets, real-world creative work requires more than isolated prompt-output interactions. It involves references, drafts, alternatives, edits, failed attempts, version relations, tool actions, evaluation signals, and human feedback, which together form an evolving project state. Existing prompt-based, chat-based, and node-based generation systems only partially support this state, as they often discard intermediate context, rely on linear conversations, or require manually specified workflows. Recent commercial systems indicate a shift toward agent-assisted creative production, but their closed architectures make it difficult to study how agents represent context, choose tools, revise artifacts, recover from failures, and maintain consistency over time. To address this gap, we introduce JarvisHub, a canvas-native creative agent harness for long-horizon multimodal creation. JarvisHub treats an editable canvas as the user workspace, the agent's external memory, action space, and shared project state, representing multimodal artifacts, dependencies, versions, and feedback as typed canvas nodes and links. Through a three-layer architecture of canvas state, protocol bridge, and agent runtime, JarvisHub enables agents to act within an inspectable and editable creative state. This design moves creative agents beyond isolated tool use toward sustained, human-steerable creative automation, where agents can progressively plan, generate, revise, and organize multimodal projects while users remain able to inspect, guide, and intervene throughout the process.
Read the full abstract

All authors Yunlong Lin, Zixu Lin, Zhaohu Xing, Biqiang Li, Chenxin Li, Haonan Wang, Haitao Wu, Hengyu Liu, Jianghai Chen, Kaituo Feng, Kaixin Li, Shawn Chen, Shijue Huang, Sixiang Chen, Tsung-Yi Ho, Wenxuan Huang, Xiangyan Liu, Xiaomeng Hu, Xuanhua He, Yan Sun, Yunqing Zhao, Zhiqin Yang, Zehan Wang, Zhengyang Tang, Tianyu Pang, Xiangyu Yue

Computer Vision

SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion

Kavish Jhaveri and Arya Shah

Existing vector-sketch models treat recognition and generation as separate tasks, leaving a gap for streaming interfaces that must understand a drawing as it is being made. We present SketchMamba, a single causal sequence model that continuously classifies a sketch from any partial prefix while simultaneously generating its continuation. We achieve this by applying a dense per-step classification loss to a selective state-space backbone. Evaluated on a 58-class subset of the Quick, Draw! dataset, SketchMamba yields 94.93% final-step accuracy and a progressive-accuracy Area Under the Curve (AUC) of 0.706, crossing 90% of its final accuracy by the time 70% of the strokes are drawn. In a matched-budget comparison, the 1.55 million-parameter backbone ties a causal Transformer while outperforming recurrent and convolutional baselines. Ablations confirm that the dense supervision regime, rather than the architecture alone, drives the early-prediction capability. The results demonstrate that a single causal hidden state can unify progressive recognition and autoregressive generation without auxiliary encoders or task-specific branching.
Read the full abstract

Computer Vision

Neuromorphic Object Detection: An In-Depth Study and Future Directions

Jianing Li, Dianze Li, Arren Glover et al. (+5 more)

Conventional frame-based cameras face significant challenges in detecting objects under high-speed motion blur or in low-light environments. Neuromorphic cameras provide asynchronous visual streams with high temporal resolution and a wide dynamic range, offering a promising solution for object detection under challenging conditions. Despite the development of numerous models and the emergence of various applications in neuromorphic object detection, there is still a lack of deep understanding and standardized benchmarks to assess progress and address key challenges. In this paper, we provide a comprehensive survey and benchmark of existing neuromorphic object detection algorithms. Specifically, we first present a problem description, review the available datasets, and revisit the evaluation metrics. We then explore existing neuromorphic object detection approaches from various perspectives, including event representation, temporal modeling, multimodal fusion, asynchronous processing, low-latency processing, and energy-efficient computing. Furthermore, we evaluate a wide range of representative neuromorphic object detection models and offer detailed analyses of the comparative results. Finally, we discuss unresolved issues in neuromorphic object detection and propose potential future research directions. We hope this survey and benchmark will be a valuable resource for researchers and provide guidance for future advancements in neuromorphic object detection.
Read the full abstract

All authors Jianing Li, Dianze Li, Arren Glover, Xiaopeng Fan, Guoqi Li, Chiara Bartolozzi, Ryad B. Benosman, Yonghong Tian

Computer Vision

D3O: Dynamic Distribution Distillation for Ordinal Regression

Chunlai Dong, Yaojun Hu, Yuyang Xu et al. (+2 more)

Ordinal regression is widely used in scenarios where labels are discrete yet inherently ordered. In practice, however, ordinal labels are often obtained by discretizing underlying continuous semantics through subjective human judgment, resulting in ambiguous boundaries and annotation noise. Such uncertainty challenges existing methods that rely on fixed supervision targets, which may reinforce biased ordering under subjective annotations. To address this limitation, we propose D3O, a dynamic distribution distillation framework that replaces static supervision with training-driven evolution of ordinal label distributions via self-distillation. Specifically, we introduce a contrastive ordinal-aware label enhancement module that leverages vision-language alignment to recover refined label distributions capturing both inter-class ambiguity and instance-level uncertainty. Furthermore, we design a CDF-based cross-layer interaction distillation mechanism to propagate cumulative ordinal structure across network hierarchy, ensuring consistent ordinal geometry in intermediate representations. Extensive experiments on four general ordinal regression tasks demonstrate that our proposed D3O consistently outperforms existing approaches, particularly under severe class imbalance and noisy supervision. These results highlight the effectiveness of dynamic supervision in learning robust ordinal representations beyond fixed targets. The code will be publicly available.
Read the full abstract

All authors Chunlai Dong, Yaojun Hu, Yuyang Xu, Haochao Ying, Jian Wu

Computer Vision

GaitFace: A Multimodal Dataset for Long-Range Person Identification

Alain Komaty, Luis S. Luevano, Vidit Vidit et al. (+3 more)

Efficient border control is becoming a significant global challenge, mainly due to severe congestion and extended passenger waiting times. To mitigate these bottlenecks and facilitate passenger flow, biometric technologies are increasingly deployed to streamline identity verification and enhance crossing efficiency. Technical limitations frequently impede biometric identification, particularly in long-range surveillance, where systems must deal with adverse atmospheric conditions and degraded image quality. While high-quality frameworks like BRIAR exist, they are frequently restricted to specific government agencies. This paper introduces GaitFace, a new public dataset that contains face and gait data captured at long distances. To ensure that the research reflects authentic border scenarios, we use Pre-Enrollment data, where a traveler registers via a mobile device, and "In-the-Wild" captures, which records individuals at a distance across multiple viewing angles and different cameras. Benchmarking SOTA face and gait models reveals that current architectures fail under low-resolution and elevated viewpoints despite success with optical assistance. GaitFace exposes these critical vulnerabilities, providing a rigorous public benchmark to drive more robust, unconstrained biometric research.
Read the full abstract

All authors Alain Komaty, Luis S. Luevano, Vidit Vidit, Anjith George, Zeina Al Amine, Sébastien Marcel

Computer Vision

Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks

Qi Ming, Zheng Zhou, Haitian Yang et al. (+4 more)

Bounding boxes are fundamental for object localization in visual detection tasks. Among them, oriented bounding boxes are widely used in visual detection tasks, which provide a more precise directional representation. Generally, IoU-based losses are widely adopted to optimize box regression. However, we observed that IoU-driven box optimization suffers from two key issues: (1) it relies solely on geometric properties while ignoring semantic cues; (2) orientation optimization suffers from unstable gradients, causing oscillations in orientation convergence. In this paper, we propose a Fractional Semantic IoU loss to achieve unified semantic-geometric learning with gradient stabilization. First, we design a semantic similarity metric to guide IoU optimization, building a Semantic IoU loss (SIoU loss) with an adaptive gradient gating mechanism. Then, we revisit the gradient instability issue in oriented box optimization and extend the SIoU loss to a fractional-order formulation to build the Fractional Semantic IoU loss (FrSIoU loss). The FrSIoU loss accumulates historical IoU states to regularize abnormal gradients during bounding box optimization process. Extensive experiments demonstrate that our approach achieves stable performance gains across different bounding box formulations and diverse visual detection tasks. The code will be available on GitHub.
Read the full abstract

All authors Qi Ming, Zheng Zhou, Haitian Yang, Xudong Zhao, Mingjing Zhao, Liuqian Wang, Nanqing Liu

Computer Vision

ATCNet-CIAM for Multi-Session Motor Imagery EEG Signal Classification

Le Huu Son Hai, Nguyen Chi Hai, Truong Viet Vu et al. (+3 more)

Motor imagery (MI)-based electroencephalography is widely used in non-invasive brain–computer interfaces (BCIs), but robust decoding remains challenging due to inter-subject variability and cross-session non-stationarity. This work proposes ATCNet-CIAM, an enhanced attention temporal convolutional network that integrates a lightweight channel-integrated attention module (CIAM) into the ATCNet framework to improve channel-spatial feature representation for MI decoding. The proposed model is evaluated on BCI Competition IV-2a, BCI Competition IV-2b, and the multi-day WBCIC-MI dataset under standard, within-session, and cross-session protocols. Experimental results show that ATCNet-CIAM achieves 86.32% accuracy on BCI IV-2a and 87.96% on BCI IV-2b under the standard protocol, while reaching 89.46% and 83.64% in the within-session WBCIC-MI on 2C and 3C, respectively. The proposed framework consistently improves classification stability and robustness under session-varying conditions, and ablation study confirms the complementary contribution of the proposed architectural components.
Read the full abstract

All authors Le Huu Son Hai, Nguyen Chi Hai, Truong Viet Vu, Nguyen Phuc Nguyen, Nguyen Thai Anh, Ngo Hoang Tu

Computer Vision

Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction

Chaonan Ji, Jinwei Qi, Peng Zhang et al. (+1 more)

We present a real-time human-centric world model for upper-body interactive generation, aiming to synthesize coherent local world dynamics centered on a person, where coordinated body, hand, and facial motions evolve jointly with controllable human-object discrete interaction. To this end, we adopt a continuous-discrete joint control scheme with two complementary components: a continuous human state and a discrete interaction state. For continuous human-state control, we introduce a unified implicit representation based on multi-scale motion encoding, in which motion latents from the upper body, hands, and face are fused into a shared latent space. This multi-scale design improves expressiveness across different spatial scales, captures fine-grained human dynamics more effectively, and enables direct control without explicit retargeting. For discrete object interaction-state control, we represent object contact using a small set of language-encoded discrete interaction states, where text serves as an explicit interaction-state command, such as no contact or grasp, rather than an open-ended generation prompt, and we further construct a dedicated rendering pipeline for human-object interaction data to supervise such discrete interaction states. By combining continuous implicit human-state control with discrete interaction-state control, our model enables precise modeling of how a person moves and interacts with the local environment, including controllable changes to nearby scene states. Finally, we distill the model for efficient streaming real-time inference, achieving 25 FPS on two H100 GPUs. Experiments demonstrate improved fine-grained motion fidelity, more realistic hand-object coordination, and effective real-time interaction, establishing a practical step beyond motion reproduction toward real-time human-centric world modeling.
Read the full abstract

All authors Chaonan Ji, Jinwei Qi, Peng Zhang, Bang Zhang

Computer Vision

MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

Zhijing Cheng, Xuancheng Zhang, Donglin Di et al. (+4 more)

End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a compact context and a downstream planner predicts trajectories conditioned on this context. We argue that this one-way perception-to-planning interface forces sensor inputs into a compact representation, losing the fine-grained details critical for planning. Moreover, by constraining the planner to this compressed context, it is difficult to leverage the rich representations offered by modern vision foundation models. To address these issues, we propose MOJITO, a unified sensor-to-action framework for end-to-end autonomous driving built on modal joint learning. MOJITO removes the cascaded interface and instead performs block-wise Modal Joint Attention that simultaneously updates action, image, and LiDAR features, allowing the planner to directly access multi-modal features during action generation. MOJITO achieves 88.9 PDMS on the NAVSIM v1 dataset and 88.4 EPDMS on the more challenging NAVSIM v2 dataset, setting a new state-of-the-art. Extensive experiments further demonstrate strong scalability, instruction following, and diverse trajectory generation. Code and models are available at https://github.com/mumucc01/MOJITO.
Read the full abstract

All authors Zhijing Cheng, Xuancheng Zhang, Donglin Di, Lei Fan, Baorui Ma, Hao Li, Xun Yang

Computer Vision

MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation

Yuqi Liu, Shengju Qian, Tianyuan Qu et al. (+5 more)

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to maintain long-horizon visual history for trajectory consistency while executing actions with low latency. Existing video-based VLN approaches typically struggle to satisfy both demands simultaneously. To address these challenges, we propose MemVLN, a novel VLN framework that achieves state-of-the-art performance with real-time inference efficiency (14 FPS). MemVLN utilizes a visual encoder to process continuous observations and a Large Language Model (LLM) to interpret instructions and generate actions. Central to our approach is an Episodic Memory management that applies pyramidal resolutions. This mechanism concentrates computation on immediate percepts while retaining compressed long-term history. Complementing to this design, we introduce Procedural Memory for fast action with a compact vocabulary of atomic mid-level actions to bypass auto-regressive decoding latency. Experiments on VLN-CE show that MemVLN-4B surpasses the baseline Qwen3-VL-4B architecture by 5.8% SR in R2R and 9.7% SR in RxR, while achieving a 7$\times$ speedup in inference latency.
Read the full abstract

All authors Yuqi Liu, Shengju Qian, Tianyuan Qu, Mingxian Lin, Zixuan Wang, Xin Wang, Bei Yu, Jiaya Jia

Computer Vision

Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation

Musa Tur Farazi and Nufayer Jahan Reza

Automated analysis of multimodal content on social networks has become a critical task for understanding public sentiment and information diffusion in the digital age. However, classifying internet memes remains computationally challenging due to the intricate interplay between visual cues and embedded, often stylized, text, particularly in low-resource languages like Bengali Language. This paper addresses the detection of political intent in Bengali memes by introducing Multimodal Cross-Attention Fusion framework. We first leverage a Vision-Language Model to extract high-fidelity OCR text from noisy meme images. Subsequently, we encode visual and textual features and synthesize them through a cross-modal multi-head attention mechanism that aligns semantic tokens with visual regions. We also investigate the integration of a domain-specific political lexicon as a knowledge prior. Experimental evaluation on the PoliMemeDecode1 dataset shows that our attention-based fusion significantly outperforms unimodal baselines and standard concatenation methods, achieving a state-of-the-art Macro-F1 of approximately 0.94. Interpretability analyzes further confirm that the model effectively learns to ground textual semantics in visual evidence.
Read the full abstract

Computer Vision

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

Shaswati Saha, Rajasekhar Anguluri and Manas Gaur

Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while preserving model utility on benign concepts. Current CETs face a trade-off between erasure robustness and utility: stronger edits erase the target more reliably but degrade utility on non-target concepts, and vice versa. This stems from how existing methods define what to erase and what to preserve. Many CETs rely on static concept banks specified manually, generated by LLMs, or selected by CLIP image-text similarity. Such banks do not model how prompts steer the model during denoising, leaving it vulnerable to triggers that reintroduce the target while suppressing nearby benign concepts. We present Preservation-aware Adaptive Ranked Subspace Expansion (PARSE), a training-free framework for robust concept erasure in latent diffusion models. Given a target, PARSE queries the diffusion model with classifier-free guidance to dynamically discover target-inducing erase concepts and nearby retain concepts in the model vocabulary. It then edits the cross-attention value space with a preservation-aware projection that removes target directions while leaving retain directions intact. For triggers beyond this vocabulary-indexed space, PARSE iteratively searches for re-emergence triggers by textual inversion and adaptively expands the erased subspace only when a new trigger direction does not conflict with retain semantics. We also introduce the Balanced Erasure Utility Score (BEUS), which combines robustness (ASR under multiple attacks) and utility preservation (FID) via bounded monotone transforms and harmonic mean aggregation. Experiments on NSFW, artistic style, and object erasure, with a large-scale robustness-utility analysis over many CET baselines, show that PARSE erases multiple concepts robustly without sacrificing post-edit utility.
Read the full abstract

Computer Vision

PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation

Pengyu Zeng, Yuqin Dai, Jun Yin et al. (+7 more)

Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin with rough strokes and refine them over time, whereas existing methods typically require their conditioning representation to be fully specified before generation, a fundamental mismatch with how design actually works. Second, the 2D floor plan is not an optional intermediate but an irreplaceable spatial contract. Once room boundaries, doors, and windows are fixed, furnishing reduces from open-ended spatial reasoning to bounded constraint satisfaction. Bypassing this contract, as existing 3D systems do by delegating layout to language models, yields overlapping rooms and implausible proportions; directly calling general-purpose language models likewise produces geometrically invalid layouts. Guided by these insights, we present PlanCraft. SketchPlan supplies the missing training signal by replaying the architect's drawing process on 80K real floor plans, producing partial sketches at every completeness level. PlanCraft-Diff progressively sharpens an incomplete sketch into a geometrically precise, vectorizable floor plan through a coarse-to-fine strategy. With the spatial contract established, PlanCraft-Agent then furnishes the scene within well-defined room boundaries. Experiments show that PlanCraft achieves a 61.1% lower FID than the best existing 2D method and surpasses existing 3D systems by 15 points in expert-rated spatial rationality, with a sketch at only 25% completion already outperforming all fully specified baselines.
Read the full abstract

All authors Pengyu Zeng, Yuqin Dai, Jun Yin, Ng Cheuk Hei, Ziyang Han, Jing Zhong, Chaoyang Shi, ZhanXiang Jin, Maowei Jiang, Shuai Lu

Computer Vision · Cross-listed from cs.LG

Learning Sampling Parameters for Diffusion Models

Arisrei Lim and Yossi Gandelsman

Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules. These parameters are typically manually chosen once and then held fixed across prompts and denoising timesteps, even though different prompts and stages of generation can benefit from different parameter values. We introduce LeSAMP, a framework for learning prompt-conditioned, timestep-varying sampling parameters. We formulate parameter selection as a reinforcement learning problem: Given a user prompt, a large language model is trained to emit schedules for the chosen sampling parameters. We optimize our model using rewards from human preference models and VLM-as-a-judge. We evaluate our model on Flux.1 [dev] and Stable Diffusion 3.5, and find that compared to baselines, LeSAMP has a win rate of up to 68.12% using human preference scores and 73.37% using VLM-as-a-judge. These gains are validated in a user study where we achieve win rates of up to 59.46% over previous baselines. Our results suggest that learned sampling-parameter policies provide a complementary approach to existing post-training methods for improving diffusion model outputs.
Read the full abstract

Computer Vision

VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation

Tianxiao Chen, Hanmo Chen, Huajin Chen et al. (+3 more)

Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficult with standard text and image conditions. The core challenge is a conditioning bottleneck: material response, contact interaction, deformation, and motion trajectory are continuous and relational physical cues that are hard to specify exhaustively in language but can be demonstrated naturally by video. We propose VIPER, a Visual In-Context Physics Reasoning framework for reference-guided image-to-video generation. Given a target image, a brief target prompt, and a reference video, VIPER treats the reference as a dense visual demonstration of the desired physical process rather than an appearance template. It uses a Multimodal Large Language Model (MLLM) to extract reference-derived physical cues and guide a pretrained image-to-video generator through a hierarchical training strategy, enabling physical behavior transfer while preserving the visual prior of the base generator. To support this setting, we construct VIPER-19K, a curated dataset with material, trajectory, and physical-impact annotations, together with filtered reference-target pairs. Experiments on an unseen validation set show that VIPER achieves stronger reference-video physical similarity and higher human preference than representative video generation and video-as-prompt baselines, while maintaining competitive general video quality. Qualitative results further demonstrate that VIPER can transfer reference-derived physical behavior to new target scenes without requiring carefully engineered prompts.
Read the full abstract

All authors Tianxiao Chen, Hanmo Chen, Huajin Chen, Bo Li, Qi Ye, Peng-Tao Jiang

Computer Vision

Robust 6-DoF Object Pose Tracking with Built-In Recovery under Occlusions and Rapid Object Motions

Balázs Opra, Léo Ghafari, Thomas Stewart et al. (+1 more)

Real-time 6-DoF object pose tracking is essential for many robotics applications, and several approaches exist. Yet even today's approaches remain unreliable under temporary full occlusions and rapid object motions. Once tracking is lost, most methods struggle to detect the failure and recover automatically, often requiring manual re-initialization. In this paper, we address the problem of robust model-based 6-DoF tracking of unseen objects from RGB-D data, especially in scenarios with occlusion and fast motion. We propose a novel method that combines efficient learning-based keypoint matching with optimization-based alignment and introduces a novel failure detection and recovery module. Our system monitors pose reliability, detects tracking divergence or occlusions, and performs a global re-detection and pose estimation step that robustly verifies recovery candidates before resuming tracking. Our evaluation on standard tracking benchmarks and on a new dataset of occluded and fast-moving scenes shows that our method matches state-of-the-art accuracy on easy tracking sequences, maintains high tracking speed at 57.6 frames per second, and provides the most robust tracking performance under challenging conditions. Thus, we believe that our approach is a relevant step forward in robust 6-DoF object tracking from RGB-D data.
Read the full abstract

All authors Balázs Opra, Léo Ghafari, Thomas Stewart, Cyrill Stachniss

Computer Vision · Cross-listed from eess.IV

Direction-adaptive Mamba: Spatial-Frequency Dual-Domain Collaborative Learning for PolSAR Image Classification

Junfei Shi, Yu Cheng, Haojia Zhang et al. (+3 more)

Deep learning dominates polarimetric synthetic aperture radar (PolSAR) image classification, with Mamba architectures serving as favorable backbones due to linear complexity and strong global modeling capacity. However, existing PolSAR Mamba methods have two critical flaws: pure spatial processing discards fine-grained edges and textures, and fixed scanning patterns fail to model direction-variant anisotropic scattering and weak boundaries essential for PolSAR physical analysis. This work proposes DA-Mamba, a direction-adaptive Mamba framework with dual-domain collaborative learning for PolSAR classification. Equipped with an edge-aligned direction-adaptive scanning scheme, DA-Mamba captures long-range spatial dependencies and accurate boundary details. It adopts the Non-Subsampled Contourlet Transform (NSCT) to separate PolSAR data into low-frequency global components and multi-directional high-frequency subbands, extracting anisotropic structural features from high-frequency information while preserving global context via low-frequency branches. A dual-domain collaborative learning module further integrates spatial scattering and frequency-domain representations to strengthen feature discriminability. Evaluated on three real-world PolSAR datasets, DA-Mamba surpasses state-of-the-art methods, verifying the efficacy of the proposed adaptive scanning and dual-domain fusion designs. Code will be publicly available.
Read the full abstract

All authors Junfei Shi, Yu Cheng, Haojia Zhang, Wenqiang Hua, Junhuai Li, Maoguo Gong

Computer Vision

Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance

Weixiang Zhou, Jiabei Zuo, Yuhao Wang et al. (+3 more)

Multi-modal object Re-Identification (ReID) aims to retrieve specific objects by integrating complementary information from multiple modalities. However, existing multi-modal ReID methods do not effectively address background interference suppression or achieve tri-modal alignment, instead focusing on pairwise feature fusion. Moreover, many current aggregation approaches suffer from high computational complexity. To address these limitations, we propose PRISM, a novel multi-modal ReID framework built upon Prompt-S6 (PS6) and semantic-aware knowledge guidance. PS6 maintains the linear complexity and strong sequence modeling capability of Mamba while enabling efficient cross-modal interaction. Leveraging these advantages, we design two key components: Semantic-Driven Token Pruning (SDTP) and Progressive Fusion Network (PFN). Parsing semantic priors from the segmentation foundation models, the SDTP then leverages these priors and applies dynamic token pruning to suppress background noise and refine feature representations. The PFN progressively aggregates multi-modal features to achieve tri-modal alignment and fully exploit modality complementarity. With the proposed modules, PRISM generates more robust multi-modal representations under complex scenarios. Extensive experiments on four multi-modal object ReID benchmarks demonstrate the effectiveness and efficiency of our approach. The source code is available at https://github.com/zw-absin/PRISM.
Read the full abstract

All authors Weixiang Zhou, Jiabei Zuo, Yuhao Wang, Cong Wang, Huchuan Lu, Zhixun Su

Computer Vision

Omni-Prune: Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language Models

Yiming Zhong, Chang Nie and Caifeng Shan

Omnimodal large language models (OmniLLMs) are rapidly extending multimodal reasoning to cover synchronized audio and video. However, the resulting audio-video token sequences are long, leading to high prefill latency and GPU memory usage at inference time. Existing token pruning methods, designed mainly for vision-only inputs, miss both the cross-modal links between audio and video and the user query that decides which content matters. To bridge this gap, we present Omni-Prune, a training-free, query-aware audio-visual token pruning framework that jointly removes redundancy from both modalities while keeping task-relevant cross-modal evidence. Specifically, Omni-Prune first splits the token sequence into adaptive time windows placed at audio saliency peaks, then scores audio and video tokens on a single scale that combines encoder attention with text-query relevance, and pairs related audio-video tokens so that they are kept together. Within each window, a final K-medoids step then selects a few representative tokens, adding diverse cues that score-based selection alone would miss. Extensive experiments demonstrate that Omni-Prune outperforms established baseline methods, delivering up to 3.25x prefill speedup and 1.3x memory reduction while retaining over 99% of full-model performance.
Read the full abstract

Saturday 25 July

Computer Vision

Adaptive Interpolatory Curve Subdivision with Learned Local Angles

Hassan Ugail and Newton Howard

Curve subdivision is pivotal in computer graphics for generating smooth geometric objects from control polygons. Interpolatory subdivision is especially attractive because the refined curve is guaranteed to pass through the designer's control points. Classical four-point and six-point schemes preserve this property, but their behaviour is governed by a single global tension parameter, limiting their ability to adapt across flat regions, sharp turns and varying local geometries. We introduce an adaptive local-angle formulation that keeps the interpolatory structure intact while learning how each new vertex should be inserted. A compact edge-wise predictor assigns one insertion angle per edge, while the original vertices are copied exactly at every refinement level. Interpolation is therefore a structural property of the operator and does not depend on the trained weights. The same predictor is used with geometry-specific geodesic primitives on the Euclidean plane, the two-sphere and the Poincaré disk. Under a matched-density evaluation protocol, the method reduces nearest-neighbour error by factors of five to seventeen over the best validation-tuned fixed-tension baseline, and by about 1.8 over centripetal Catmull-Rom in the Euclidean case. It also substantially reduces bending energy and tangent roughness, while remaining competitive with separately trained per-geometry models.
Read the full abstract

Computer Vision

A Heisenberg Lift Descriptor for Order Sensitive Online Handwriting Recognition

Hassan Ugail and Newton Howard

Online handwriting recognition systems typically represent pen trajectories through fixed-length Euclidean shape descriptors that capture the spatial outline of each stroke, but are insensitive to the order in which that outline is produced. Two strokes that trace the same region of the plane in opposite directions are indistinguishable to any such order-blind representation, yet their traversal directions may carry decisive class information in characters where loop orientation and stroke sequencing matter. This paper introduces a Heisenberg-lift framework that addresses this gap through a compact, interpretable, order-sensitive augmentation for online pen-trajectory features. The simplest instance is the terminal signed area, a single parameter-free scalar appended to an existing Euclidean descriptor at negligible computational cost. Evaluated on two standard online handwriting benchmarks, this one-scalar addition, consistently raises classifier accuracy over the Euclidean baseline. On the hardest character pair in our study, the letters o and y, the signed area alone achieves perfect separation while the Euclidean baseline falls short. The advantage grows further under additive coordinate noise, a practically relevant degradation in pen-trajectory data. A richer fifteen-dimensional extension, derived from a noncommutative Heisenberg-group subdivision scheme, provides additional gains in noisy and loop-structured conditions. Dimension-matched statistical controls confirm that all improvements reflect geometric information rather than feature-count inflation. The resulting descriptor is lightweight, closed-form, and directly interpretable, making it a practical augmentation for online handwriting and related document-trajectory classification pipelines in which the direction of stroke execution carries discriminative information.
Read the full abstract

Computer Vision

Hold-Out Self-Validation Cannot Certify Photogrammetric Accuracy: Saturation and Blindness to Coherent Distortion

Behnam Asadi

Internal self-consistency cannot certify the accuracy of a photogrammetric reconstruction, and the failure is structural rather than a matter of tuning. This matters because hold-out self-validation scores are increasingly offered as quality evidence for metric deliverables whose correctness is otherwise unknown without an external survey. We formalise a track-leakage-free hold-out protocol: a deterministic image subset is withheld, and each withheld view is re-localised against only those 3D points supported by two or more retained images, so no view is tested against structure it helped create. We evaluate it on five GNSS-referenced captures across four sites, 13 ETH3D scenes, a EuRoC flight and 30 IMC 2025 scenes. The protocol is well-posed but does not measure accuracy. It saturates: the internal confidence score stays pinned at 1.00 while true error swings 14.1x within one capture. It is blind to coherent distortion: fragmenting corruption is caught, but internally self-consistent, globally distorted models are not, and were wrong by 55-106 m at confidence 1.00 at three of four captures. On IMC 2025 it separates failed from successful reconstructions (rho = 0.68) yet ranks nothing among the successful (rho = 0.01). Track-leakage-free hold-out measures internal geometric consistency: a fragmentation warning, not a substitute for control-point accuracy assessment.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

Semantic Semi-Incremental Data-Association-Free Object SLAM

Yihao Zhang, Jungseok Hong and John J. Leonard

Data association between landmark measurements and landmark variables has long been a central challenge in SLAM, as estimation accuracy depends critically on associating measurements with the correct landmark variables. Recent advances in deep learning have created new opportunities for the problem; data association can now leverage not only positional measurements but also semantic information about object landmarks, such as class labels from neural object detectors and feature vectors from visual foundation models. In this paper, we present a generalized data-association-free SLAM framework that jointly estimates data associations, robot poses, landmark positions, and landmark semantics from odometry, and positional and semantic measurements of landmarks. The proposed framework (i) creates a synergy between data association and landmark semantics estimation; (ii) adopts a semi-incremental estimation scheme for improved accuracy and computational efficiency; and (iii) provides a principled justification, guidelines, and heuristics for landmark-number estimation, improving the interpretability and practical usability of the framework. The proposed framework and algorithms are evaluated on synthetic and real-world datasets with two types of semantic information, class labels and real-valued feature vectors, and demonstrate superior performance compared to strong baselines.
Read the full abstract

Computer Vision

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

Ioannis Maniadis Metaxas, Adrian Bulat, Alberto Baldrati et al. (+4 more)

Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge devices. While efforts to compress LVLMs focus heavily on vision token reduction or smaller language models, the vision encoder is largely overlooked, typically deployed as a monolithic, computationally heavy feature extractor. Moreover, there is no previous effort that designs a vision encoder for LVLMs directly optimized for on-device latency. In this paper, we present UltraViT, a vision encoder for LVLMs, explicitly designed and optimized for on-device performance. Specifically, by taking into account real on-device latencies, we systematically design a pyramidal architecture that strategically integrates and adapts heterogeneous spatial mixers at the macro-block level. Furthermore, to pre-train UltraViT, we propose a novel two-stage generative pre-training strategy: cultivating rich spatial features via dense distillation, followed by direct generative supervision from a capacity-mixed frozen LLM. Compared to standard contrastive and SSL, we show that our pre-training is much more effective for achieving high-level semantic grounding for UltraViT needed for the subsequent generative multimodal alignment of LVLM training. Extensive experiments demonstrate that our on-device latency-informed design combined with our tailored training strategy establishes a new state-of-the-art for efficient LVLM encoding, significantly outperforming existing encoder-centric baselines while operating on-device at nearly 1.7xthe speed.
Read the full abstract

All authors Ioannis Maniadis Metaxas, Adrian Bulat, Alberto Baldrati, Anestis Zaganidis, Yassine Ouali, Hyeonuk Kim, Georgios Tzimiropoulos

Computer Vision · Cross-listed from eess.IV

Investigating the Visual Cues of CNNs for Vascular Segmentation: A Case Study in Microscopy and Fundus Imaging

Weslley dos Santos Silva and Cesar Henrique Comin

Vascular segmentation is a standard procedure for clinical diagnosis, yet the specific visual features determining model decisions remain poorly understood. This paper investigates the visual cues Convolutional Neural Networks (CNNs) use to segment blood vessels across two distinct imaging domains: fluorescence microscopy and retinal fundus photography. We employ a series of experiments to quantify the influence of shape, texture, and receptive field on segmentation performance. First, we isolate texture and intensity by evaluating performance on patches subjected to pixel shuffling and normalization. Second, we assess global shape relevance by training models on sparse contours and centerlines. Lastly, we quantify the required spatial context by systematically varying the network's theoretical and effective receptive fields. Within the scope of the evaluated datasets, we found that pixel intensity is more relevant than texture, though networks maintain surprisingly high accuracy even when both cues are removed. Furthermore, CNNs struggle to extrapolate full vessel geometry from shape cues alone, typically relying on a relatively small effective receptive field of around 20 pixels, though global context provides a modest benefit for fundus images. While specific to the modalities studied, this methodology offers a quantitative foundation to audit and refine deep learning systems in vascular imaging.
Read the full abstract

Computer Vision

Explaining BiomedCLIP with Weighted Banzhaf Interactions Supported by Tree-Gram Parsing

Jakub Rymarski, Adam Rempała, Bartłomiej Sobieski et al. (+1 more)

Vision-Language Models (VLMs) are demonstrating significant capabilities in medical tasks like radiology analysis, yet providing faithful and interpretable explanations remains a key consideration for their responsible deployment in clinical settings. However, existing explanation methods, such as the widely used FIxLIP framework, often struggle with the fine-grained nature of modern tokenizers. The tokenization problem fragments clinical concepts—splitting terms like "saddle embolus" into scattered, meaningless subwords—which leads to noisy, semantically incoherent cross-modal attributions. Such fragmentation also results in a combinatorial explosion of interaction possibilities, obscuring the model's true reasoning. To address this, we introduce ParseFIxLIP, an extension that incorporates the Tree-Gram Parsing into the Banzhaf interaction game used by FIxLIP. This semantically informed strategy utilizes dependency parsing trees to define explanation players by grouping related text tokens into semantically coherent units. Our smart_depth grouping strategy, merging tokens according to spaCy token dependency tree, successfully mitigates concept fragmentation, yielding substantially more interpretable cross-modal interactions by unifying complex medical concepts. Quantitatively, while baselines struggled with the high dimensionality of long captions, our parsing approach maintained statistical robustness and semantic parsimony. Qualitative analysis on BiomedCLIP, validated on medical imagery (ROCOv2) and general examples, confirms that the approach accurately captures the synergistic influence of grouped words on model predictions. In conclusion, our work offers intuitive and clinically relevant insights into VLM decision-making, fulfilling the critical need for coherent explanations in the medical domain.
Read the full abstract

All authors Jakub Rymarski, Adam Rempała, Bartłomiej Sobieski, Przemysław Biecek

Computer Vision · Cross-listed from eess.IV

Codebook Capacity Governs Perceptual Quality Across Resolutions in Hierarchical Discrete Video Compression

Manikanta Kotthapalli and Banafsheh Rekabdar

Learned video codecs based on continuous latent representations typically require resolution-specific retraining or rate-distortion (RD) recalibration when scaling to new spatial resolutions, because entropy models and Lagrangian weights are tightly coupled to the operating point. We investigate whether hierarchical discrete latent codecs exhibit the same sensitivity. Using a controlled empirical study of MS-VQ-VAE video compression across codebook sizes $K \in \{128,256,512,1024\}$ and resolutions $64\times64$, $128\times128$, and $256\times256$ on UCF101, we show that perceptual quality (LPIPS) depends strongly on codebook capacity but only negligibly on spatial resolution. Fitting a log-linear model $Q(K,r) = \alpha\log_2 K + \beta\log_2 r + \gamma$ to all 12 operating points yields $\alpha=-0.0094$ ($t=-6.6$, $p<0.001$) and $\beta=-0.0009$ ($t=-0.43$, $p=0.68$, not significant), with $R^2=0.82$. Codebook capacity is therefore roughly $10\times$ more influential than spatial resolution per log-unit increase. In parallel, bottom-level entropy efficiency $\eta=H(z)/\log_2 K$ remains stable or improves with resolution (84-87% at $64\times64$; 92-94% at $256\times256$), confirming that larger spatial grids are utilized more efficiently rather than less. Across all resolutions and codebook sizes, our models outperform H.264 on LPIPS at matched or lower bitrate, with gains of 25-52% at $128\times128$ and 21-37% over H.265 at $256\times256$. These findings suggest that codebook size $K$, not spatial resolution, is the dominant design variable governing perceptual compression quality in hierarchical discrete video codecs – a property that may simplify multi-resolution deployment and inform the design of scalable discrete tokenizers for generative video models.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

Arghya Sinha, Aditya Banerjee, Trishit Mukherjee et al. (+1 more)

Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneously offer strong denoising performance and global Lipschitz guarantees is challenging. Existing approaches enforce Lipschitz control only empirically, providing no guarantees beyond the training data. In this work, we show that by exploiting the action of permutations on the image lattice, we can constrain a neural architecture that is globally nonexpansive (Lipschitz bound $\leqslant 1$). We integrate the proposed denoiser with forward imaging operators to develop a reconstruction mechanism that is provably contractive and therefore globally convergent. Experiments on standard inverse problems, such as superresolution and deblurring, demonstrate that our reconstruction performance is competitive with softly constrained baselines while providing Lipschitz guarantees.
Read the full abstract

All authors Arghya Sinha, Aditya Banerjee, Trishit Mukherjee, Kunal N. Chaudhury