3D Vision

SDFormer: Vision-based 3D Semantic Scene Completion via SAM-assisted Dual-channel Voxel Transformer ICCV 2025 SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction CVPR 2025 SE(3)-Equivariant Diffusion Models for 3D Object Analysis IJCAI 2025 Seam360GS: Seamless 360deg Gaussian Splatting from Real-World Omnidirectional Images ICCV 2025 SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography ICLR 2025 SEED4D: A Synthetic Ego-Exo Dynamic 4D Data Generator Driving Dataset and Benchmark WACV 2025 SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding CVPR 2025 Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification ICCV 2025 Seeing A 3D World in A Grain of Sand CVPR 2025 Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks CVPR 2025 Seg2Box: 3D Object Detection by Point-Wise Semantics Supervision AAAI 2025 Segment Any 3D Gaussians AAAI 2025 Segment Any 3D Object with Language ICLR 2025 SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding ICCV 2025 SEHDR: Single-Exposure HDR Novel View Synthesis via 3D Gaussian Bracketing ICCV 2025 Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences WACV 2025 Self-Calibrating Gaussian Splatting for Large Field-of-View Reconstruction ICCV 2025 Self-Correcting Robot Manipulation via Gaussian-Splatted Foresight AAAI 2025 Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis ICCV 2025 SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting CVPR 2025 Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration CVPR 2025 Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics ICCV 2025 Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States CoRL 2025 Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos ICCV 2025 Self-Supervised Spatial Correspondence Across Modalities CVPR 2025