amusi/CVPR2026-Papers-with-Code

CVPR 2026 decisions are now available on OpenReview！25.42% = 4090 / 16092 欢迎扫码加入【CVer学术交流群】，可以获取CVPR 2026等最前沿工作！这是最大的计算机视觉AI知识星球！每日更新，第一时间分享最新最前沿的计算机视觉、AIGC、扩散模型、多模态、深度学习、自动驾驶、医疗影像和遥感等方向的学习资料，快加入学起来！ Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking FastGS: Training 3D Gaussian Splatting in 100 Seconds Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues ApET: Approximation-Error Guided Token Compression for Efficient VLMs Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking MedCLIPSeg: Probabilistic Vision–Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation Open-Vocabulary Domain Generalization in Urban-Scene Segmentation U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation #3D Visual Grounding(3D视觉定位) ExpPortrait:…