CV

共 68 篇论文

cs.CV大语言模型CV

Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support

This paper presents Oph-Guid-RAG, a multimodal visual retrieval-augmented generation system designed for ophthalmology clinical decision support. The system treats guideline pages as independent evidence units and retrieves page images while preserving visual elements like tables and flowcharts. It implements a controllable retrieval framework with routing and filtering mechanisms to reduce noise while selectively introducing external evidence. The system combines query decomposition, rewriting, retrieval, reranking, and multimodal reasoning to provide traceable outputs with guideline references. Evaluated on HealthBench with doctor-based scoring, the approach significantly outperforms GPT-5.2 and GPT-5.4 on hard subsets, achieving +30.0% improvement in overall score and +10.4% to +24.4% gains in accuracy.

Oph-Guid-RAG Team

27 days ago

arXiv 2603.21925v1

cs.CV自动驾驶CV

Multi-View Deformable Convolution Meets Visual Mamba for Coronary Artery Segmentation

This paper presents MDSVM-UNet, a novel two-stage framework for accurate coronary artery segmentation from CTA images. The proposed method integrates multi-view deformable convolution with Visual Mamba state space models to effectively capture long-range dependencies in vascular structures while maintaining linear computational complexity. This approach addresses challenges in segmenting complex multi-branching coronary arteries with severe class imbalance, enabling improved diagnosis and treatment planning for cardiovascular diseases. The synergy between deformable convolutions and Mamba architecture provides an efficient solution suitable for clinical deployment in resource-constrained environments.

X. Zhang +3

27 days ago

arXiv 2603.21829v1

cs.RO自动驾驶端到端

Can a Robot Walk the Robotic Dog: Triple-Zero Collaborative Navigation for Heterogeneous Multi-Agent Systems

This paper presents Triple Zero Path Planning (TZPP), a collaborative navigation framework for heterogeneous multi-robot systems achieving zero training, zero prior knowledge, and zero simulation requirements. The system employs a coordinator-explorer architecture where a Unitree G1 humanoid robot performs task coordination while a Unitree Go2 quadruped robot explores and identifies feasible paths using guidance from a multimodal large language model. The framework is evaluated across diverse indoor and outdoor environments including obstacle-rich and landmark-sparse settings, demonstrating robust and human-comparable navigation efficiency. By eliminating reliance on traditional training and simulation pipelines, TZPP provides a practical approach for real-world deployment of heterogeneous robot cooperation with strong adaptability to unseen scenarios.

TZPP Authors

27 days ago

arXiv 2603.21723v1

cs.CV自动驾驶CV

BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration

This paper addresses bimanual robot manipulation tasks where coordinated actions between two robotic arms are required for complex object interactions. The work introduces a Collaborative Preparatory Manipulation framework that enables robots to perform sequential preparatory actions - such as pushing objects to accessible positions or lifting items - to facilitate subsequent goal-directed manipulations by the other arm. The proposed visual affordance-based approach first anticipates the final task objective and then generates appropriate preparatory manipulations, requiring deep understanding of object geometry, spatial relationships, and semantic properties. By learning from demonstrations and employing vision-based affordance recognition, the framework achieves effective bimanual coordination for tasks involving objects that are difficult to grasp directly.

BiPreManip Authors

27 days ago

arXiv 2603.21679v1

cs.CV自动驾驶端到端

Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis

Image deraining is a critical low-level computer vision task essential for robust outdoor surveillance and autonomous driving systems. While deep learning methods have shown success in aligned training settings, they typically experience significant performance degradation when applied to unseen Out-of-Distribution scenarios due to domain discrepancies between synthetic training data and real-world rain dynamics. This paper proposes a cross-scenario deraining adaptation framework that eliminates the need for paired rainy observations in target domains, utilizing only rain-free background images. The method incorporates a Superpixel Generation module that extracts stable structural priors from source domains using Simple Linear Iterative Clustering, enabling effective rain removal across diverse scenarios.

Anonymous

27 days ago

arXiv 2603.21661v1

cs.RO自动驾驶端到端

RTD-RAX: Fast, Safe Trajectory Planning for Systems under Unknown Disturbances

This paper presents RTD-RAX, a runtime-assurance extension of Reachability-based Trajectory Design that addresses two critical limitations of standard RTD implementations: conservatism from worst-case reachable-set overapproximations and inability to handle real-time disturbances. The framework combines a non-conservative RTD formulation for rapid goal-directed trajectory generation with mixed monotone reachability for fast disturbance-aware safety certification. When proposed trajectories fail safety verification under uncertainty, a repair procedure finds nearby safe trajectories that maintain progress toward the goal while guaranteeing safety under real-time disturbances. This approach enables provably safe, real-time trajectory planning for autonomous systems operating in uncertain environments.

S. K. S. Mitraz +3

27 days ago

arXiv 2603.21635v1

cs.CV自动驾驶CV

PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation

Brain tumor MRI segmentation is essential for clinical diagnosis and treatment planning, enabling accurate lesion detection and radiotherapy target delineation. However, tumor lesions occupy only a small fraction of the volumetric space, resulting in severe spatial sparsity, while existing segmentation networks often overlook clinically observed spatial priors of tumor occurrence, leading to redundant feature computation over extensive background regions. To address this issue, we propose PGR-Net (Prior-Guided ROI Reasoning Network) - an explicit ROI-aware framework that incorporates a data-driven spatial prior set to capture the distribution and scale characteristics of tumor lesions, providing global guidance for more stable segmentation. Leveraging these priors, PGR-Net introduces a hierarchical Top-K ROI decision mechanism that progressively selects the most confident lesion candidate regions across encoder layers to improve localization precision.

PGR-Net Authors

27 days ago

arXiv 2603.21626v1

cs.CVCVTransformer

Efficient Zero-Shot AI-Generated Image Detection

This paper addresses the critical challenge of detecting AI-generated images produced by text-to-image models. The proposed method is training-free and measures representation sensitivity to structured frequency perturbations, enabling detection of subtle manipulations between real and synthetic images. The approach uses only a single Fourier transform for perturbation generation, making it computationally lightweight and achieving one to two orders of magnitude faster inference than existing training-free detectors. Extensive experiments on challenging benchmarks including the OpenFake benchmark demonstrate superior performance over state-of-the-art methods.

Anonymous

27 days ago

arXiv 2603.21619v1

cs.CV自动驾驶端到端

HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labeling

Regressing 3D rotations of objects from 2D images is a crucial yet challenging task, with broad applications in autonomous driving, virtual reality, and robotic control. This paper proposes a hardness-aware curriculum learning framework for semi-supervised rotation regression that dynamically selects pseudo-labeled samples based on their difficulty, progressing from easy to complex examples. The approach addresses limitations of rigid entropy-based pseudo-label filtering by introducing both multi-stage and adaptive curriculum strategies to effectively distinguish between reliable and unreliable unlabeled samples.

HACMatch Authors

27 days ago

arXiv 2603.21583v1

cs.CV自动驾驶CV

Mind over Space: Can Multimodal Large Language Models Mentally Navigate?

This paper addresses the limitation of Multimodal Large Language Models (MLLMs) in embodied agents, which struggle with spatial reasoning across extensive spatiotemporal scales. The authors introduce Video2Mental, a benchmark that evaluates mental navigation capabilities by requiring models to construct hierarchical cognitive maps from long egocentric videos and generate landmark-based path plans. The research draws inspiration from cognitive science, exploring how biological intelligence uses mental navigation and spatial simulation prior to action. Benchmarking results demonstrate that mental navigation capabilities do not naturally emerge from standard pre-training, with frontier MLLMs showing significant challenges in zero-shot scenarios. Planning accuracy is verified through simulator-based physical interaction, providing a comprehensive evaluation framework for embodied AI systems.

Unknown

27 days ago

arXiv 2603.21577v1

cs.CVCVTransformer

VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection

This paper presents VIGIL, a novel part-centric structured forensic framework for deepfake detection using multimodal large language models. The approach employs a plan-then-examine pipeline where the model first plans which facial parts warrant inspection based on global visual cues, then examines each part with independently sourced forensic evidence. A stage-gated injection mechanism delivers part-level forensic evidence only during examination to ensure unbiased part selection. The framework is inspired by expert forensic practice and aims to improve the reliability of deepfake detection by separating evidence generation from manipulation localization, addressing the issue of hallucinated explanations in current MLLM-based methods.

VIGIL Authors

27 days ago

arXiv 2603.21526v1

cs.CVCVTransformer

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

This paper presents RoboAlign, a systematic framework for improving vision-language-action models (VLAs) by enhancing embodied reasoning capabilities in multimodal large language models (MLLMs). The key innovation involves sampling action tokens through zero-shot natural language reasoning and refining them using reinforcement learning to improve action accuracy. The approach effectively bridges the modality gap between language understanding and low-level robot actions, facilitating knowledge transfer from multimodal LLMs to embodied agents. Experimental validation demonstrates that training VLAs with this framework leads to reliable performance improvements in robotic manipulation tasks.

RoboAlign Authors

28 days ago

arXiv 2603.21341v1

cs.CV自动驾驶端到端

Enhancing Brain Tumor Classification Using Vision Transformers with Colormap-Based Feature Representation on BRISC2025 Dataset

This study presents a deep learning framework for multi-class brain tumor classification from magnetic resonance imaging scans using Vision Transformers enhanced with colormap-based feature representation. The proposed method leverages transformer architectures to capture long-range dependencies while incorporating color mapping techniques to emphasize structural and intensity variations in MRI scans. Experiments on the BRISC2025 dataset containing glioma, meningioma, pituitary tumor, and non-tumor cases demonstrate superior performance with 98.90% accuracy, significantly outperforming baseline approaches. The framework utilizes standard metrics including accuracy, precision, recall, F1-score, and AUC for comprehensive evaluation.

Anonymous Authors

28 days ago

arXiv 2603.21234v1

cs.CV端到端CV

GAPG: Geometry Aware Push-Grasping Synergy for Goal-Oriented Manipulation in Clutter

Grasping target objects is a fundamental skill for robotic manipulation, but in cluttered environments with stacked or occluded objects, a single-step grasp is often insufficient. This paper proposes a geometry-aware push-grasp synergy framework that leverages point cloud data to integrate grasp and push evaluation. The grasp evaluation module analyzes the geometric relationship between the gripper's point cloud and the points enclosed within its closing region to determine grasp feasibility and stability. Guided by this analysis, the push evaluation module predicts how pushing actions influence future graspable space, enabling the robot to effectively manipulate objects in complex cluttered scenarios.

GAPG Authors

28 days ago

arXiv 2603.21195v1

cs.RO自动驾驶CV

Architecture for Multi-Unmanned Aerial Vehicles based Autonomous Precision Agriculture Systems

This paper presents an architectural framework for deploying multiple coordinated UAVs in precision agriculture applications. The system addresses key challenges including autonomous mission planning, coordinated data acquisition, and efficient image processing for field analysis. Various computational tasks such as path planning, communication protocols, and field mapping are integrated to enable minimal human intervention during agricultural operations. The architecture provides a comprehensive end-to-end solution supporting cooperative multi-UAV deployment, optimized for precision agriculture monitoring and intervention tasks.

Unknown

28 days ago

arXiv 2603.21183v1

cs.CV自动驾驶CV

CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop Evaluation

This paper presents CounterScene, a novel framework that enables structured counterfactual reasoning in generative Bird's Eye View (BEV) world models for safety-critical driving scenario generation. The approach addresses the challenge of creating realistic yet adversarially effective safety scenarios by introducing causal adversarial agent identification to determine critical agents and conflict types. CounterScene develops a conflict-aware interactive world model using causal interaction graphs to explicitly model dynamic inter-agent dependencies. The framework performs minimal interventions through stage-adaptive counterfactual guidance, effectively bridging the gap between realism and adversarial robustness in autonomous driving safety evaluation.

CounterScene Authors

28 days ago

arXiv 2603.21104v1

cs.CV自动驾驶端到端

Single-Eye View: Monocular Real-time Perception Package for Autonomous Driving

This paper presents LRHPerception, a real-time monocular perception package designed specifically for autonomous driving applications. The system leverages monocular camera video to interpret the surrounding environment by combining the computational efficiency of end-to-end learning with detailed local mapping methodologies. It achieves comprehensive perception through integrated object tracking and prediction, road segmentation, and depth estimation capabilities. The unified framework processes monocular images into a five-channel tensor containing RGB, road segmentation, and pixel-level depth information, enhanced with object detection and trajectory prediction. Experimental results demonstrate impressive real-time performance at 29 FPS on a single GPU, representing a 555% speedup compared to baseline approaches.

LRHPerception Team

28 days ago

arXiv 2603.21061v1

cs.CVCVTransformer

Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation

View transformers process multi-view observations to predict actions and have shown impressive performance in robotic manipulation. Existing methods typically extract static visual representations in a view-specific manner, leading to inadequate 3D spatial reasoning ability and a lack of dynamic adaptation. Taking inspiration from how the human brain integrates static and dynamic views, we propose Cortical Policy, a novel dual-stream view transformer for robotic manipulation that jointly reasons from static-view and dynamic-view streams. The static-view stream enhances spatial understanding by aligning features of geometrically consistent keypoints extracted from a pretrained 3D foundation model. The dynamic-view stream achieves adaptive adjustment through position-aware pretraining of an egocentric gaze estimation model, computationally replicating the human cortical dorsal pathway. The complementary view representations enable improved robotic manipulation performance.

Cortical Policy Authors

28 days ago

arXiv 2603.21051v1

cs.CV自动驾驶CV

A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors

This paper presents a temporal action localization framework specifically designed for driver monitoring systems in autonomous driving applications. The framework employs a two-stage pipeline combining VideoMAE-based feature extraction with an Augmented Self-Mask Attention detector to identify hazardous driving behaviors from in-cabin video streams. A Spatial Pyramid Pooling-Fast module captures multi-scale temporal features for improved localization accuracy. The approach is optimized for transportation safety checkpoints and fleet management assessment systems, demonstrating a trade-off between model capacity and computational efficiency.

Anonymous Authors

28 days ago

arXiv 2603.21048v1

cs.CVCV3D检测

Geometrically Plausible Object Pose Refinement using Differentiable Simulation

This paper addresses the challenge of geometrically infeasible pose hypotheses in object pose estimation, particularly for dexterous manipulation scenarios. The authors propose a multi-modal approach combining differentiable physics simulation, differentiable rendering, and visuo-tactile sensing to refine object poses while ensuring physical consistency. The method significantly reduces intersection volume errors between objects and robotic hands by 73% under accurate initial estimates and over 87% under high uncertainty, outperforming ICP-based approaches. By integrating physical constraints into pose optimization, this work enables robots to achieve more reliable manipulation by ensuring estimated object poses respect both geometric accuracy and physical reality.

Anonymous Authors

28 days ago

arXiv 2603.20992v1