Computer Vision

Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video CVPR 2025 Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models EMNLP 2025 Look Around Before Locating: Considering Content and Structure Information for Visual Grounding AAAI 2025 Looking in the Mirror: A Faithful Counterfactual Explanation Method for Interpreting Deep Image Classification Models ICCV 2025 LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers ICML 2025 LUCAS: Layered Universal Codec Avatars CVPR 2025 Lyapunov Perception Contracts for Operating Design Domains L4DC 2025 MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction CVPR 2025 MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining CVPR 2025 Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion ICCV 2025 MaskPrompt: Open-Vocabulary Affordance Segmentation with Object Shape Mask Prompts AAAI 2025 MATCHA: Towards Matching Anything CVPR 2025 Matching While Perceiving: Enhance Image Feature Matching with Applicable Semantic Amalgamation AAAI 2025 Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval ACL 2025 Maximizing the Position Embedding for Vision Transformers with Global Average Pooling AAAI 2025 MDP-Omni: Parameter-free Multimodal Depth Prior-based Sampling for Omnidirectional Stereo Matching ICCV 2025 MeasureXpert: Automatic Anthropometric Measurement Extraction from Two Unregistered, Partial, Posed, and Dressed Body Scans ICCV 2025 MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data CVPR 2025 MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh ICCV 2025 MICE: Mixture of Image Captioning Experts Augmented e-Commerce Product Attribute Value Extraction ACL 2025 Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching ICCV 2025 Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning ICLR 2025 MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations WACV 2025 MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction CVPR 2025 MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models CVPR 2025