3D Vision

Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features ICCV 2025 Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models ICCV 2025 Novel View Synthesis Under Large-Deviation Viewpoint for Autonomous Driving AAAI 2025 Novel View Synthesis with Pixel-Space Diffusion Models CVPR 2025 NPL-MVPS: Neural Point-Light Multi-View Photometric Stereo WACV 2025 NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics CVPR 2025 NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images CVPR 2025 NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer ICLR 2025 OAMaskFlow: Occlusion-Aware Motion Mask for Scene Flow AAAI 2025 ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting ICCV 2025 ObjectReact: Learning Object-Relative Control for Visual Navigation CoRL 2025 ObjVariantEnsemble: Advancing Point Cloud LLM Evaluation in Challenging Scenes with Subtly Distinguished Objects AAAI 2025 OccFlowNet: Occupancy Estimation via Differentiable Rendering and Occupancy Flow WACV 2025 OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction WACV 2025 OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering ICCV 2025 Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy ICLR 2025 Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition CVPR 2025 Occlusion-robust Stylization for Drawing-based 3D Animation ICCV 2025 OccMamba: Semantic Occupancy Prediction with State Space Models CVPR 2025 Occupancy Learning with Spatiotemporal Memory ICCV 2025 OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving ICCV 2025 OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS ICCV 2025 Odd-One-Out: Anomaly Detection by Comparing with Neighbors CVPR 2025 ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos CVPR 2025 OffsetOPT: Explicit Surface Reconstruction without Normals CVPR 2025