Computer Vision

Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors CVPR 2026 Portable Active Learning for Object Detection CVPR 2026 PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback CVPR 2026 Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality CVPR 2026 Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting CVPR 2026 RADAR: VQ-VAE Decoder of VAR is a Good Student for Restoring Against Degradation by Acceleration CVPR 2026 RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation CVPR 2026 Real-Time Neural Video Compression with Unified Intra and Inter Coding CVPR 2026 REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting CVPR 2026 ReFTA: Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning CVPR 2026 ResDiT: Evoking the Intrinsic Resolution Scalability in Diffusion Transformers CVPR 2026 Rethinking Asymmetric Quantization: Hidden Symmetry in Vision Model Weights CVPR 2026 Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation CVPR 2026 RFDM: Residual Flow Diffusion Models for Video Editing CVPR 2026 RHCNet: Residual-Guided Hierarchical Calibration Network for Robust Underwater Object Detection CVPR 2026 RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization CVPR 2026 Scale Space Diffusion CVPR 2026 Scaling Dense Event-Stream Pretraining from Visual Foundation Models CVPR 2026 SDGS: Spatial Difference Guided Gaussian Splatting for Simultaneous Localization and 3D Reconstruction CVPR 2026 SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection CVPR 2026 SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras CVPR 2026 SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction CVPR 2026 Sparse-View Localization via Online Neural 3D Regression CVPR 2026 SPE-MVS: Spatial Position Encoding Enhanced Multi-View Stereo with Monocular Depth Priors CVPR 2026 Spike-driven Discrete Aggregation for Event-based Object Detection CVPR 2026