TimSong412 / OmniTrackFast
Official Code For Track Everything Everywhere Fast and Robustly
☆39Updated 2 weeks ago
Related projects: ⓘ
- Tame a Wild Camera: In-the-Wild Monocular Camera Calibration☆64Updated 8 months ago
- [CVPR2024] SANeRF-HQ: Segment Anything for NeRF in High Quality.☆36Updated 3 months ago
- Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)☆106Updated last week
- [ECCV 2024] Decomposition Betters Tracking Everything Everywhere☆101Updated 2 months ago
- ☆76Updated 4 months ago
- ☆52Updated 2 months ago
- Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)☆110Updated 6 months ago
- ☆66Updated this week
- ☆50Updated 7 months ago
- [ICCV 2023] Rendering Humans from Object-Occluded Monocular Videos☆42Updated 7 months ago
- ViTA: Video Transformer Adaptor for Robust Video Depth Estimation☆43Updated 10 months ago
- GNeuVox: Generalizable Neural Voxels for Fast Human Radiance Fields☆60Updated last year
- Official Implementation for "Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation", CVPR 2023.☆46Updated last year
- [ICCV 2023] Instance Neural Radiance Field☆41Updated 7 months ago
- Code for our CVPR 2023 paper on online, temporally consistent depth estimation.☆87Updated last year
- Official codebase for 3D-LFM paper. Accepted at CVPR, 2024.☆55Updated 2 months ago
- [NeurIPS 2023 Spotlight] Code for "Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion"☆59Updated 10 months ago
- [TPAMI'23] NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction☆64Updated last year
- ConsistentNeRF Enhances Neural Radiance Fields with 3D Consistency for Sparse View Synthesis☆72Updated 11 months ago
- Code for "Learning Human Mesh Recovery in 3D Scenes" CVPR 2023☆84Updated last year
- Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection (ICCV23)☆35Updated 11 months ago
- [CVPR 2024] MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation☆105Updated 4 months ago
- Official implementation of the 2024 ECCV paper SHIC: Shape-Image Correspondences with no Keypoint Annotation☆25Updated last month
- [ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models☆113Updated 3 weeks ago
- ☆42Updated last year
- [ECCV 2024] Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation☆28Updated 2 weeks ago
- [NeurIPS 2023] 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection☆41Updated 5 months ago
- ☆14Updated 7 months ago
- The official implementation of "GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation". (Xie et al., arXiv 2406.06…☆72Updated 2 months ago
- Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation☆131Updated last week