Computer Vision
Yantao Li, Qiang Hui, Chenyang Yan et al. (+8 more)
Reinforcement learning has recently improved the
reasoning ability of Large
Language Models and
Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process
hallucinations–cases where models reach the right answer while misperceiving visual evidence. We address this process-level misalignment with PaLMR, a framework that aligns not only outcomes but also the
reasoning process itself. PaLMR comprises two complementary components: a perception-aligned data layer that constructs process-aware
reasoning data with structured pseudo-ground-truths and verifiable visual facts, and a process-aligned optimisation layer that constructs a hierarchical reward fusion scheme with a process-aware scoring function to encourage visually faithful chains-of-thought and improve training stability. Experiments on Qwen2.5-VL-7B show that our approach substantially reduces
reasoning hallucinations and improves visual
reasoning fidelity, achieving state-of-the-art results on HallusionBench while maintaining strong performance on MMMU, MathVista, and MathVerse. These findings indicate that PaLMR offers a principled and practical route to process-aligned
multimodal reasoning, advancing the reliability and interpretability of MLLMs.
Read the full abstract ▾
All authors Yantao Li, Qiang Hui, Chenyang Yan, Kanzhi Cheng, Fang Zhao, Chao Tan, Huanling Gao, Jianbing Zhang, Kai Wang, Xinyu Dai, Shiguo Lian
Computer Vision
Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models
Ci Zhang, Zhaojun Ding, Chence Yang et al. (+7 more)
Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from
diffusion models. It promises high efficiency and robustness, offering an attractive alternative to traditional fine-tuning or editing-based unlearning. However, in this paper we uncover a hidden danger behind this promising paradigm. We find that the locations of pruned weights, typically set to zero during unlearning, can act as side-channel signals that leak critical information about the erased concepts. To verify this vulnerability, we design a novel attack framework capable of reviving erased concepts from pruned
diffusion models in a fully data-free and training-free manner. Our experiments confirm that
pruning-based unlearning is not inherently secure, as erased concepts can be effectively revived without any additional data or retraining. Extensive experiments on
diffusion-based unlearning based on concept related weights lead to the conclusion: once the critical concept-related weights in
diffusion models are identified, our method can effectively recover the original concept regardless of how the weights are manipulated. Finally, we explore potential defense strategies and advocate safer
pruning mechanisms that conceal
pruning locations while preserving unlearning effectiveness, providing practical insights for designing more secure
pruning-based unlearning frameworks.
Read the full abstract ▾
All authors Ci Zhang, Zhaojun Ding, Chence Yang, Jun Liu, Xiaoming Zhai, Shaoyi Huang, Beiwen Li, Xiaolong Ma, Jin Lu, Geng Yuan
Computer Vision
From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification
Vasiliy Kudryavtsev, Kirill Borodin, German Berezin et al. (+3 more)
Automated animal identification is a practical task for reuniting lost pets with their owners, yet current systems often struggle due to limited
dataset scale and reliance on unimodal visual cues. This study introduces a
multimodal verification framework that enhances visual features with semantic identity priors derived from synthetic textual descriptions. We constructed a massive training corpus of 1.9 million photographs covering 695,091~unique animals to support this investigation. Through systematic ablation studies, we identified SigLIP2-
Giant and E5-Small-v2 as the optimal
vision and text backbones. We further evaluated fusion strategies ranging from simple concatenation to adaptive gating to determine the best method for integrating these modalities. Our proposed approach utilizes a gated fusion mechanism and achieved a Top-1 accuracy of 84.28% and an Equal Error Rate of 0.0422 on a comprehensive test protocol. These results represent an 11% improvement over leading unimodal baselines and demonstrate that integrating synthesized semantic descriptions significantly refines decision boundaries in large-scale pet re-identification.\\\\ Conference update. This work was accepted to the FGVC13 Workshop at CVPR 2026. We thank Vadim Ezhov and Nikolai Shcheglov for their help with the poster presentation and demonstration at the conference.
Read the full abstract ▾
All authors Vasiliy Kudryavtsev, Kirill Borodin, German Berezin, Kirill Bubenchikov, Grach Mkrtchian, Alexander Ryzhkov
Computer Vision
Social-JEPA: Emergent Geometric Isomorphism
Youjin Wang
World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate
agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or coordination. After training, their internal representations exhibit a striking emergent property: the two latent spaces are related by an approximate linear isometry, enabling transparent translation between them. This
geometric consensus survives large viewpoint shifts and scant overlap in raw pixels. Leveraging the learned
alignment, a classifier trained on one
agent can be ported to the other with no additional gradient steps, while
distillation-like migration accelerates later learning and markedly reduces total compute. The findings reveal that predictive learning objectives impose strong regularities on representation geometry, suggesting a lightweight path to interoperability among decentralized
vision systems. The code is available at https://anonymous.4open.science/r/Social-JEPA-5C57.
Read the full abstract ▾
Computer Vision
MME: Mixture of Mesh Experts with Random Walk Transformer Gating
Amir Belder and Ayellet Tal
In recent years, various methods have been proposed for mesh analysis, each offering distinct advantages and often excelling on different object classes. We present a novel Mixture of Experts (MoE) framework designed to harness the complementary strengths of these diverse approaches. We propose a new gate architecture that encourages each expert to specialise in the classes it excels in. Our design is guided by two key ideas: (1) random walks over the mesh surface effectively capture the regions that individual experts attend to, and (2) an
attention mechanism that enables the gate to focus on the areas most informative for each expert's decision-making. To further enhance performance, we introduce a dynamic loss balancing scheme that adjusts a trade-off between diversity and similarity losses throughout the training, where diversity
prompts expert specialization, and similarity enables knowledge sharing among the experts. Our framework achieves state-of-the-art results in mesh classification,
retrieval, and semantic
segmentation tasks. Our code is available at: https://github.com/amirbelder/MME-Mixture-of-Mesh-Experts.
Read the full abstract ▾
Computer Vision
COMBAT: Conditional World Models for Behavioral Agent Training
Anmol Agarwal, Pranay Meshram, Sumer Singh et al. (+5 more)
Recent advances in
video generation have spurred the development of world models capable of simulating 3D-consistent environments and interactions with static objects. However, a significant limitation remains in their ability to model dynamic, reactive
agents that can intelligently influence and interact with the world. To address this gap, we introduce COMBAT, a real-time, action-controlled world model trained on the complex 1v1 fighting game Tekken 3. Our work demonstrates that
diffusion models can successfully simulate a dynamic opponent that reacts to player actions, learning its behavior implicitly. Our approach utilizes a 1.2 billion parameter
Diffusion Transformer, conditioned on latent representations from a deep compression autoencoder. We employ state-of-the-art techniques, including causal
distillation and
diffusion forcing, to achieve real-time inference. Crucially, we observe the emergence of sophisticated
agent behavior by training the model solely on single-player inputs, without any explicit supervision for the opponent's policy. Unlike traditional imitation learning methods, which require complete action labels, COMBAT learns effectively from partially observed data to generate responsive behaviors for a controllable Player 1. We present an extensive study and introduce novel evaluation methods to
benchmark this emergent
agent behavior, establishing a strong foundation for training interactive
agents within
diffusion-based world models.
Read the full abstract ▾
All authors Anmol Agarwal, Pranay Meshram, Sumer Singh, Saurav Suman, Andrew Lapp, Shahbuland Matiana, Louis Castricato, Spencer Frazier
Computer Vision
NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code
Seemandhar Jain, Keshav Gupta, Kunal Gupta et al. (+1 more)
The proliferation of neural radiance field (NeRF) research requires significant efforts to reimplement papers before building upon them. We introduce NERFIFY, a multi-
agent framework that reliably converts NeRF research papers into trainable Nerfstudio plugins, in contrast to generic paper-to-code methods and frontier models like GPT-5 that usually fail to produce runnable code. NERFIFY achieves domain-specific executability through six key innovations: (1) Context-free grammar (CFG): LLM synthesis is constrained by Nerfstudio formalized as a CFG, ensuring generated code satisfies architectural invariants. (2) Graph-of-Thought code synthesis: Specialized multi-file-
agents generate repositories in topological dependency order, validating contracts and errors at each node. (3) Compositional citation recovery:
Agents automatically retrieve and integrate components (samplers, encoders, proposal networks) from citation graphs of references. (4) Visual feedback: Artifacts are diagnosed through PSNR-minima ROI analysis, cross-view
geometric validation, and VLM-guided patching to iteratively improve quality. (5) Knowledge enhancement: Beyond reproduction, methods can be improved with novel optimizations. (6) Benchmarking: An evaluation framework is designed for NeRF paper-to-code synthesis across 30 diverse papers. On papers without public implementations, NERFIFY achieves visual quality matching expert human code (+/-0.5 dB PSNR, +/-0.2 SSIM) while reducing implementation time from weeks to minutes. NERFIFY demonstrates that a domain-aware design enables code translation for complex
vision papers, potentiating accelerated and democratized reproducible research. Code, data and implementations will be publicly released.
Read the full abstract ▾
All authors Seemandhar Jain, Keshav Gupta, Kunal Gupta, Manmohan Chandraker
Computer Vision · Cross-listed from eess.IV
Efficient Conformal Volumetry for Template-Based Segmentation
Matt Y. Cheung, Ashok Veeraraghavan and Guha Balakrishnan
Template-based
segmentation, a widely used paradigm in medical imaging, propagates anatomical labels via deformable registration from a labeled atlas to a target image, and is often used to compute volumetric biomarkers for downstream decision-making. While conformal prediction (CP) provides finite-sample valid intervals for scalar metrics, existing
segmentation-based uncertainty quantification (UQ) approaches either rely on learned model features, often unavailable in classic template-based pipelines, or treat the registration process as a black box, resulting in overly conservative intervals when applied directly in output space. We introduce ConVOLT, a CP framework that achieves efficient volumetric UQ by conditioning calibration on properties of the estimated deformation field from template-based
segmentation. ConVOLT calibrates a learned volumetric scaling factor from deformation space features. We evaluate ConVOLT on template-based
segmentation tasks involving global, regional, and label volumetry across multiple
datasets and registration methods. ConVOLT achieves target coverage while producing substantially tighter intervals than output-space conformal baselines. Our work paves way to exploit the registration process for efficient UQ in medical imaging pipelines.
Read the full abstract ▾
Computer Vision
Neural Functional Alignment Space: Brain-Referenced Representation of Artificial Neural Networks
Ruiyu Yan, Hanqi Jiang, Yi Pan et al. (+4 more)
We propose the Neural Functional
Alignment Space (NFAS), a
brain-referenced representational framework for characterizing artificial neural networks on equal functional grounds. NFAS departs from conventional
alignment approaches that rely on layer-wise features or task-specific activations by modeling the intrinsic dynamical
evolution of stimulus representations across network depth. Specifically, we model layer-wise
embeddings as a depth-wise dynamical trajectory and apply Dynamic Mode Decomposition (DMD) to extract the stable mode. This representation is then projected into a biologically anchored coordinate system defined by distributed neural responses. We also introduce the Signal-to-Noise Consistency Index (SNCI) to quantify cross-model consistency at the modality level. Across 45 pretrained models spanning
vision, audio, and
language, NFAS reveals structured organization within this
brain-referenced space, including modality-specific clustering and cross-modal convergence in integrative cortical systems. Our findings suggest that representation dynamics provide a principled basis for
Read the full abstract ▾
All authors Ruiyu Yan, Hanqi Jiang, Yi Pan, Xiaobo Li, Tianming Liu, Xi Jiang, Lin Zhao
Computer Vision
DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents
Zikang Xu, Ruinan Jin and Xiaoxiao Li
Fairness in medical
agents is becoming critical as tool-using clinical AI systems orchestrate specialized
vision and
language modules for tasks such as chest X-ray question answering. While these medical AI
agents can improve flexibility, their added pipeline complexity also creates new pathways for demographic bias beyond standalone models. We present DUCK, Decomposing Unfairness in Chest X-ray
agents, a systematic audit of
fairness in tool-using chest X-ray
agents instantiated with MedRAX. To localize where disparities arise, we introduce a stage-wise
fairness decomposition that separates end-to-end bias from three
agent-specific sources: tool exposure bias, or utility gaps conditioned on tool presence; tool transition bias, or subgroup differences in tool-routing patterns; and model
reasoning bias, or subgroup differences in synthesis behaviors. Extensive experiments on tool-using agentic frameworks across five driver backbones reveal that demographic gaps persist in end-to-end performance, with equalized odds up to 20.79% and the lowest
fairness-utility tradeoff down to 28.65%. Intermediate behaviors, including tool usage, transition patterns, and
reasoning traces, exhibit distinct subgroup disparities that are not predictable from end-to-end evaluation alone. For example, conditioned on
segmentation-tool availability, the subgroup utility gap reaches as high as 50%. Our findings underscore the need for process-level
fairness auditing and debiasing to ensure the equitable deployment of clinical agentic systems. Code: https://github.com/Nanboy-Ronan/DUCK.
Read the full abstract ▾
Computer Vision
Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models
Zhenyu Zhou, Defang Chen, Siwei Lyu et al. (+2 more)
Text-to-image
diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free sampling acceleration methods are typically developed independently, leaving the overall performance and compatibility among these methods unexplored. In this paper, we bridge this gap by systematically elucidating the design space, and our comprehensive experiments identify the sampling time schedule as the most pivotal factor. Inspired by the
geometric properties of
diffusion models revealed through the Frenet-Serret formulas, we propose constant total rotation schedule (TORS), a scheduling strategy that ensures uniform
geometric variation along the sampling trajectory. TORS outperforms previous training-free acceleration methods and produces high-quality images with 10 sampling steps on Flux.1-Dev and Stable
Diffusion 3.5. Extensive experiments underscore the adaptability of our method to unseen models, hyperparameters, and downstream applications. Code is available at https://github.com/zju-pi/TORS.
Read the full abstract ▾
All authors Zhenyu Zhou, Defang Chen, Siwei Lyu, Chun Chen, Can Wang
Computer Vision
Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder
Adam Marcus, Paul Bentley and Daniel Rueckert
Stroke is a major cause of death and disability worldwide. Accurate outcome and
evolution prediction has the potential to revolutionize stroke care by individualizing clinical decision-making leading to better outcomes. However, despite a plethora of attempts and the rich data provided by neuroimaging, modelling the ultimate fate of
brain tissue remains a challenging task. In this work, we apply recent ideas in the field of
diffusion probabilistic models to generate a self-supervised semantically meaningful stroke representation from Computed
Tomography (CT) images. We then improve this representation by extending the method to accommodate longitudinal images and the time from stroke onset. The effectiveness of our approach is evaluated on a
dataset consisting of 5,824 CT images from 3,573 patients across two medical centers with minimal labels. Comparative experiments show that our method achieves the best performance for predicting next-day severity and functional outcome at discharge.
Read the full abstract ▾
Computer Vision
BornoViT: A Novel Efficient Vision Transformer for Bengali Handwritten Basic Characters Classification
Rafi Hassan Chowdhury, Naimul Haque and Kaniz Fatiha
Handwritten character classification in the Bengali script is a significant challenge due to the complexity and variability of the characters. The models commonly used for classification are often computationally expensive and data-hungry, making them unsuitable for resource-limited
languages such as Bengali. In this experiment, we propose a novel, efficient, and lightweight
Vision Transformer model that effectively classifies Bengali handwritten basic characters and digits, addressing several shortcomings of traditional methods. The proposed solution utilizes a deep convolutional neural network (DCNN) in a more simplified manner compared to traditional DCNN architectures, with the aim of reducing computational burden. With only 0.65 million parameters, a model size of 0.62 MB, and 0.16 GFLOPs, our model, BornoViT, is significantly lighter than current state-of-the-art models, making it more suitable for resource-limited environments, which is essential for Bengali handwritten character classification. BornoViT was evaluated on the BanglaLekha Isolated
dataset, achieving an accuracy of 95.77%, and demonstrating superior efficiency compared to existing state-of-the-art approaches. Furthermore, the model was evaluated on our self-collected
dataset, Bornomala, consisting of approximately 222 samples from different age groups, where it achieved an accuracy of 91.51%.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.RO
UniHM: Unified Dexterous Hand Manipulation with Vision Language Model
Zhenhao Zhang, Jiaxin Liu, Ye Shi et al. (+1 more)
Planning physically feasible dexterous hand manipulation is a central challenge in robotic manipulation and
Embodied AI. Prior work typically relies on object-centric cues or precise hand-object interaction sequences, foregoing the rich, compositional guidance of open-vocabulary instruction. We introduce UniHM, the first framework for unified dexterous hand manipulation guided by free-form
language commands. We propose a Unified Hand-Dexterous Tokenizer that maps heterogeneous dexterous-hand morphologies into a single shared codebook, improving cross-dexterous hand generalization and scalability to new morphologies. Our
vision language action model is trained solely on human-object interaction data, eliminating the need for massive real-world teleoperation
datasets, and demonstrates strong generalizability in producing human-like manipulation sequences from open-ended
language instructions. To ensure physical realism, we introduce a physics-guided dynamic refinement module that performs segment-wise joint optimization under generative and temporal priors, yielding smooth and physically feasible manipulation sequences. Across multiple
datasets and real-world evaluations, UniHM attains state-of-the-art results on both seen and unseen objects and trajectories, demonstrating strong generalization and high physical feasibility. Our project page at \href{https://unihm.github.io/}{https://unihm.github.io/}.
Read the full abstract ▾
All authors Zhenhao Zhang, Jiaxin Liu, Ye Shi, Jingya Wang
Computer Vision
Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization
Qinghui He, Haifeng Zhang, Xiuli Bi et al. (+3 more)
The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely to make classifiers data-dependent, resulting in narrow decision margins and, consequently, limited generalization ability to unseen generative models. We observe that both real and generated images intend to form clustered low-dimensional
manifolds within high-level feature spaces extracted by pre-trained visual encoders. Building on this observation, we propose a single-class attribution modeling framework that first amplifies the intrinsic differences between real and generated images by constructing a compact attribution space from any single-class training set, either composed of real images or generated ones, and then establishes a more stable decision boundary upon the enlarged separation. This process enhances class distinction and mitigates the reliance on generator-specific artifacts, thereby improving cross-model generalization. Extensive experiments show that our method generalizes well across various unseen generative models, outperforming existing detectors by as much as 7.21% in accuracy and 7.20% in cross-model generalization.
Read the full abstract ▾
All authors Qinghui He, Haifeng Zhang, Xiuli Bi, Bo Liu, Chi-Man Pun, Bin Xiao
Computer Vision
A Reconstruction System for Industrial Pipeline Inner Walls Using Panoramic Image Stitching with Endoscopic Imaging
Rui Ma, Yifeng Wang, Ziteng Yang et al. (+3 more)
Visual analysis and reconstruction of pipeline inner walls remain challenging in industrial inspection scenarios. This paper presents a dedicated reconstruction system for pipeline inner walls via industrial endoscopes, which is built on panoramic image stitching technology. Equipped with a custom graphical user interface (GUI), the system extracts key frames from endoscope
video footage, and integrates polar coordinate transformation with image stitching techniques to unwrap annular
video frames of pipeline inner walls into planar panoramic images. Experimental results demonstrate that the proposed method enables efficient processing of industrial endoscope
videos, and the generated panoramic stitched images preserve all detailed features of pipeline inner walls in their entirety. This provides intuitive and accurate visual support for defect detection and condition assessment of pipeline inner walls. In comparison with the traditional frame-by-frame
video review method, the proposed approach significantly elevates the efficiency of pipeline inner wall reconstruction and exhibits considerable engineering application value.
Read the full abstract ▾
All authors Rui Ma, Yifeng Wang, Ziteng Yang, Jing Guo, Naomi Imali Okanda, Xinghui Li
Computer Vision · Cross-listed from cs.CR
IU: Imperceptible Universal Backdoor Attack
Hsin Lin, Yan-Lun Chen, Ren-Hung Hwang et al. (+1 more)
Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal
backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we introduce a novel imperceptible universal
backdoor attack that simultaneously controls all target classes with minimal poisoning while preserving stealth. Our key idea is to leverage graph convolutional networks (GCNs) to model inter-class relationships and generate class-specific perturbations that are both effective and visually invisible. The proposed framework optimizes a dual-objective loss that balances stealthiness (measured by perceptual similarity metrics such as PSNR) and attack success rate (ASR), enabling scalable, multi-target
backdoor injection. Extensive experiments on ImageNet-1K with ResNet architectures demonstrate that our method achieves high ASR (up to 91.3%) under poisoning rates as low as 0.16%, while maintaining benign accuracy and evading state-of-the-art defenses. These results highlight the emerging risks of invisible universal
backdoors and call for more robust detection and mitigation strategies.
Read the full abstract ▾
All authors Hsin Lin, Yan-Lun Chen, Ren-Hung Hwang, Chia-Mu Yu
Computer Vision
Towards Khmer Scene Document Layout Detection
Marry Kong, Rina Buoy, Sovisal Chenda et al. (+3 more)
While document layout analysis for Latin scripts has advanced significantly, driven by the advent of large
multimodal models (LMMs), progress for the Khmer
language remains constrained because of the scarcity of annotated training data. This gap is particularly acute for scene documents, where perspective distortions and complex backgrounds challenge traditional methods. Given the structural complexities of Khmer script, such as diacritics and multi-layer character stacking, existing Latin-based layout analysis models fail to accurately delineate semantic layout units, particularly for dense text regions (e.g., list items). In this paper, we present the first comprehensive study on Khmer scene document layout detection. We contribute a novel framework comprising three key elements: (1) a robust training and benchmarking
dataset specifically for Khmer scene layouts; (2) an open-source document augmentation tool capable of synthesizing realistic scene documents to scale training data; and (3) layout detection baselines utilizing YOLO-based architectures with oriented bounding boxes (OBB) to handle
geometric distortions. To foster further research in the Khmer document analysis and recognition (DAR) community, we release our models, code, and
datasets in this gated repository (in review).
Read the full abstract ▾
All authors Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing, Masakazu Iwamura, Koichi Kise
Computer Vision
Towards Universal Khmer Text Recognition
Marry Kong, Rina Buoy, Sovisal Chenda et al. (+3 more)
Khmer is a low-resource
language characterized by a complex script, presenting significant challenges for optical character recognition (OCR). While document printed text recognition has advanced because of available
datasets, performance on other modalities, such as handwritten and scene text, remains limited by data scarcity. Training modality-specific models for each modality does not allow cross-modality transfer learning, from which modalities with limited data could otherwise benefit. Moreover, deploying many modality-specific models results in significant
memory overhead and requires error-prone routing each input image to the appropriate model. On the other hand, simply training on a combined
dataset with a non-uniform data distribution across different modalities often leads to degraded performance on underrepresented modalities. To address these, we propose a universal Khmer text recognition (UKTR) framework capable of handling diverse text modalities. Central to our method is a novel modality-aware adaptive feature selection (MAFS) technique designed to adapt visual features according to a particular input image modality and enhance recognition robustness across modalities. Extensive experiments demonstrate that our model achieves state-of-the-art (SoTA) performance. Furthermore, we introduce the first comprehensive
benchmark for universal Khmer text recognition, which we release to the community to facilitate future research. Our
datasets and models can be accessible via this gated repository\footnote{in review}.
Read the full abstract ▾
All authors Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing, Masakazu Iwamura, Koichi Kise
Computer Vision
TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
Yihui Li, Chengxin Lv, Zichen Tang et al. (+2 more)
We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a
Token-aligned Gaussian Prediction module that aligns semantically corresponding information across views directly in the feature space. Guided by coarse
token positions and fusion confidence, it aggregates multi-scale contextual features to enable long-range cross-view
reasoning and reduce redundancy from overlapping Gaussians. To further enhance pose robustness and disentangle viewpoint cues from scene semantics, TokenSplat employs learnable camera
tokens and an Asymmetric Dual-Flow Decoder (ADF-Decoder) that enforces directionally constrained communication between camera and image
tokens. This maintains clean factorization within a feed-forward architecture, enabling coherent reconstruction and stable pose estimation without iterative refinement. Extensive experiments demonstrate that TokenSplat achieves higher reconstruction fidelity and novel-view synthesis quality in pose-free settings, and significantly improves pose estimation accuracy compared to prior pose-free methods. Project page: https://kidleyh.github.io/tokensplat/.
Read the full abstract ▾
All authors Yihui Li, Chengxin Lv, Zichen Tang, Hongyu Yang, Di Huang
Computer Vision
STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification
Xingguo Xu, Zhanyu Liu, Weixiang Zhou et al. (+5 more)
Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard
token filtering or simple fusion strategies, which can lead to the loss of discriminative cues and increased background interference. To address these challenges, we propose STMI, a novel multi-modal learning framework consisting of three key components: (1)
Segmentation-Guided Feature Modulation (SFM) module leverages SAM-generated masks to enhance foreground representations and suppress background noise through learnable
attention modulation; (2) Semantic
Token Reallocation (STR) module employs learnable query
tokens and an adaptive reallocation mechanism to extract compact and informative representations without discarding any
tokens; (3) Cross-Modal Hypergraph Interaction (CHI) module constructs a unified hypergraph across modalities to capture high-order semantic relationships. Extensive experiments on public
benchmarks (i.e., RGBNT201, RGBNT100, and MSVR310) demonstrate the effectiveness and robustness of our proposed STMI framework in multi-modal ReID scenarios.
Read the full abstract ▾
All authors Xingguo Xu, Zhanyu Liu, Weixiang Zhou, Yuansheng Gao, Junjie Cao, Yuhao Wang, Jixiang Luo, Dell Zhang
Computer Vision
SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTion
Guoquan Wei, Liu Shi, Shaoyu Wang et al. (+3 more)
Noise and artifacts during computed
tomography (CT) scans are a fundamental challenge affecting disease diagnosis. However, current methods either involve excessively long reconstruction times or rely on data-driven models for optimization, failing to adequately consider the valuable information inherent in the data itself, especially medical 3D data. This work proposes a reconstruction method under ultra-low raw data conditions, requiring no external data and avoiding lengthy pre-training processes. By leveraging spatial nonlocal similarity and the conjugate properties of the projection domain to generate pseudo-3D data for self-supervised training, high-fidelity results can be achieved in a very short time. Extensive experiments demonstrate that this method not only mitigates detector-induced ring artifacts but also exhibits unprecedented capabilities in detail recovery. This method provides a new paradigm for research using unlabeled raw projection data. Code is available at https://github.com/yqx7150/SCOUT.
Read the full abstract ▾
All authors Guoquan Wei, Liu Shi, Shaoyu Wang, Mohan Li, Cunfeng Wei, Qiegen Liu
Computer Vision
CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion
Yushan Han, Hui Zhang, Qiming Xia et al. (+2 more)
Collaborative perception empowers autonomous
agents to share complementary information and overcome perception limitations. While early fusion offers more perceptual complementarity and is inherently robust to model heterogeneity, its high communication cost has limited its practical deployment, prompting most existing works to favor intermediate or late fusion. To address this, we propose a communication-efficient early Collaborative perception framework that incorporates
LiDAR Completion to restore scene completeness under sparse transmission, dubbed as CoLC. Specifically, the CoLC integrates three complementary designs. First, each neighbor
agent applies Foreground-Aware Point Sampling (FAPS) to selectively transmit informative points that retain essential structural and contextual cues under bandwidth constraints. The ego
agent then employs Completion-Enhanced Early Fusion (CEEF) to reconstruct dense pillars from the received sparse inputs and adaptively fuse them with its own observations, thereby restoring spatial completeness. Finally, the Dense-Guided Dual
Alignment (DGDA) strategy enforces semantic and
geometric consistency between the enhanced and dense pillars during training, ensuring consistent and robust feature learning. Experiments on both simulated and real-world
datasets demonstrate that CoLC achieves superior perception-communication trade-offs and remains robust under heterogeneous model settings. The code is available at https://github.com/CatOneTwo/CoLC.
Read the full abstract ▾
All authors Yushan Han, Hui Zhang, Qiming Xia, Yi Jin, Yidong Li
Computer Vision
Specializing Foundation Models via Mixture of Low-Rank Experts for Comprehensive Head CT Analysis
Youngjin Yoo, Han Liu, Bogdan Georgescu et al. (+14 more)
Foundation models pre-trained on large-scale
datasets demonstrate strong transfer learning capabilities; however, their adaptation to complex multi-label diagnostic tasks-such as comprehensive head CT finding detection-remains understudied. Standard parameter-efficient fine-tuning methods such as LoRA apply uniform adaptations across pathology types, which may limit performance for diverse medical findings. We propose a Mixture of Low-Rank Experts (MoLRE) framework that extends LoRA with multiple specialized low-rank adapters and unsupervised soft routing. This approach enables conditional feature adaptation with less than 0.5% additional parameters and without explicit pathology supervision. We present a comprehensive
benchmark of MoLRE across six state-of-the-art medical imaging foundation models spanning 2D and 3D architectures, general-domain, medical-domain, and head CT-specific pretraining, and model sizes ranging from 7M to 431M parameters. Using over 70,000 non-contrast head CT scans with 75 annotated findings-including hemorrhage, infarction, trauma, mass lesions, structural abnormalities, and chronic changes-our experiments demonstrate consistent performance improvements across all models. Gains vary substantially: general-purpose and medical-domain models show the largest improvements (DINOv3-Base: +4.6%; MedGemma: +4.3%), whereas 3D CT-specialized or very large models show more modest gains (+0.2-1.3%). The combination of MoLRE and MedGemma achieves the highest average detection AUC of 0.917. These findings highlight the importance of systematic benchmarking on target clinical tasks, as pretraining domain, architecture, and model scale interact in non-obvious ways.
Read the full abstract ▾
All authors Youngjin Yoo, Han Liu, Bogdan Georgescu, Yanbo Zhang, Sasa Grbic, Michael Baumgartner, Thomas J. Re, Jyotipriya Das, Poikavila Ullaskrishnan, Eva Eibenberger, Andrei Chekkoury, Uttam K. Bodanapally, Savvas Nicolaou, Pina C. Sanelli, Thomas J. Schroeppel, Yvonne W. Lui, Eli Gibson
Computer Vision
Direct low-field MRI super-resolution using undersampled k-space
Daniel Tweneboah Anyimadu, Mohammed M. Abdelsamea and Ahmed Karam Eldaly
Low-field
magnetic resonance imaging (MRI) provides affordable access to diagnostic imaging but suffers from prolonged acquisition and limited image quality. Accelerated imaging can be achieved with k-space undersampling, while super-resolution (SR) and image quality transfer (IQT) methods typically rely on spatial-domain post-processing. In this work, we propose a novel framework for reconstructing high-field MR like images directly from undersampled low-field k-space. Our approach employs a k-space dual channel U-Net that processes the real and imaginary components of undersampled k-space to restore missing frequency content. Experiments on low-field
brain MRI demonstrate that our k-space-driven image enhancement consistently outperforms the counterpart spatial-domain method. Furthermore, reconstructions from undersampled k-space achieve image quality comparable to full k-space acquisitions. To the best of our knowledge, this is the first work that investigates low-field MRI SR/IQT directly from undersampled k-space.
Read the full abstract ▾
Computer Vision
Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning
Wentao Huang, Weimin Lyu, Peiliang Lou et al. (+8 more)
Computational pathology has advanced rapidly in recent years, driven by domain-specific image encoders and growing interest in using
vision-
language models to answer natural-
language questions about diseases. Yet, the core problem behind pathology question-answering remains unsolved, considering that a gigapixel slide contains far more information than necessary for a given question. Pathologists naturally navigate tissue and morphology complexity by scanning broadly, and zooming in selectively according to the clinical questions. Current models, in contrast, rely on uniform patch sampling or broad
attention maps, often attending equally to irrelevant regions while overlooking key visual evidence. In this work, we try to bring models closer to how humans actually examine slides. We propose a question-guided, tissue-aware, and coarse-to-fine
retrieval framework, HistoSelect, that consists of two key components: a group sampler that identifies question-relevant tissue regions, followed by a patch selector that retrieves the most informative patches within those regions. By selecting only the most informative patches, our method becomes significantly more efficient: reducing visual
token usage by 70% on average, while improving accuracy across three pathology QA tasks. Evaluated on 356,000 question-answer pairs, our approach outperforms existing methods and produces answers grounded in interpretable, pathologist-consistent regions. Our results suggest that bringing human-like search and
attention patterns into WSI
reasoning is a promising direction for building practical and reliable pathology VLMs. Code is available at https://github.com/winston52/HistoSelect.
Read the full abstract ▾
All authors Wentao Huang, Weimin Lyu, Peiliang Lou, Qingqiao Hu, Xiaoling Hu, Shahira Abousamra, Wenchao Han, Ruifeng Guo, Jiawei Zhou, Chao Chen, Chen Wang
Computer Vision
Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding
Ying Liu, Yudong Han, Kean Shi et al. (+1 more)
Multimodal Large
Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic knowledge embedded in Large
Language Models (LLMs). However, existing approaches typically rely on final-layer visual features or learnable multi-layer fusion, which often fail to sufficiently exploit hierarchical visual cues without explicit cross-layer interaction design. In this work, we propose a
Memory-Augmented Adapter (Mema) within the
vision encoder. Specifically, Mema maintains a stateful
memory that accumulates hierarchical visual representations across layers, with its
evolution conditioned on both query
embeddings and step-wise visual features. A portion of this
memory is selectively injected into
token representations via a feedback mechanism, thereby mitigating the attenuation of fine-grained visual cues from shallow layers. Designed as a lightweight and plug-and-play module, Mema integrates seamlessly into pretrained
vision encoders without modifying the vanilla backbone architecture. Only a minimal set of additional parameters requires training, enabling adaptive visual feature refinement while reducing training overhead. Extensive experiments across multiple
benchmarks demonstrate that Mema consistently improves performance, validating its effectiveness in complex
multimodal reasoning tasks. The code have been released at https://github.com/Sisiliu312/Mema.
Read the full abstract ▾
All authors Ying Liu, Yudong Han, Kean Shi, Liyuan Pan
Computer Vision
RC-GeoCP: Geometric Consensus for 4D Radar-Camera Collaborative Perception
Xiaokai Bai, Lianqing Zheng, Runwei Guan et al. (+3 more)
Collaborative perception (CP) extends sensing range through feature sharing, but most systems remain
LiDAR-centric. Camera and 4D radar sensing combines dense semantics with lower-cost range–velocity measurements, yet exploiting their complementarity across
agents remains difficult. Camera depth ambiguity produces spatially diffuse BEV evidence, while sparse transmission couples the choice of evidence to its subsequent contribution. Separate acquisition and aggregation objectives can assign conflicting source preferences to the retained evidence. We propose RC-GeoCP, connecting radar-grounded representation with persistent receiver–source attribution.
Geometric Structure Rectification (GSR) uses radar-conditioned deformable sampling and gated calibration to construct grounded BEV features before communication. On these features, Uncertainty-Aware Communication (UAC) combines receiver demand with semantic confidence and radar support in a pre-delivery responsibility field that selects sparse support within fixed quotas. The Consensus-Driven Assembler (CDA) maps the same field into a bounded source mixture, carrying acquisition preferences into assembly. Persistent attribution coordinates spatial selection and source weighting across sparse transmission. Across two
datasets and three aggregation backbones, RC-GeoCP consistently improves detection. Its sparse model retains 98.6%/96.6% of dense AP@0.7 at 10.88/4.95 MB per link. Code will be released.
Read the full abstract ▾
All authors Xiaokai Bai, Lianqing Zheng, Runwei Guan, Siyuan Cao, Songkai Wang, Huiliang Shen
Computer Vision
Xiaohan Zhao, Xinyi Shang, Jiacheng Liu et al. (+1 more)
Dataset pruning has been widely studied for 2D images to remove redundancy and accelerate training, while particular
pruning methods for 3D data remain largely unexplored. In this work, we study
dataset pruning for 3D data, where its observed common long-tail class distribution nature make optimization under conventional evaluation metrics Overall Accuracy (OA) and Mean Accuracy (mAcc) inherently conflicting, and further make
pruning particularly challenging. To address this, we formulate
pruning as approximating the full-data expected risk with a weighted subset, which reveals two key errors: coverage error from insufficient representativeness and prior-mismatch bias from inconsistency between subset-induced class weights and target metrics. We propose representation-aware subset selection with per-class retention quotas for long-tail coverage, and prior-invariant teacher supervision using calibrated soft labels and
embedding-geometry
distillation. The retention quota also serves as a switch to control the OA-mAcc trade-off. Extensive experiments on 3D
datasets show that our method can improve both metrics across multiple settings while adapting to different downstream preferences. Our code is available at https://github.com/XiaohanZhao123/3D-
Dataset-
Pruning.
Read the full abstract ▾
All authors Xiaohan Zhao, Xinyi Shang, Jiacheng Liu, Zhiqiang Shen
Computer Vision
Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
Fanghua Yu, Jinfan Hu, Zhiyuan You et al. (+5 more)
This position paper argues that the evaluation of modern visual processing systems should no longer be driven primarily by single-metric image quality assessment
benchmarks, particularly in the era of generative and perception-oriented methods. Image restoration exemplifies this divergence: while objective IQA metrics enable reproducible, scalable evaluation, they have increasingly drifted apart from human perception and user preferences. We contend that this mismatch risks constraining innovation and misguiding research progress across visual processing tasks. Rather than rejecting metrics altogether, this paper calls for a rebalancing of evaluation paradigms, advocating a more human-centered, context-aware, and fine-grained approach to assessing the visual models' outcomes.
Read the full abstract ▾
All authors Fanghua Yu, Jinfan Hu, Zhiyuan You, Xiang Yin, Hongyu An, Xinqi Lin, Chao Dong, Jinjin Gu