TomTomTommi / stereoanyvideo
Stereo Any Video: Temporally Consistent Stereo Matching
☆122Updated this week
Alternatives and similar repositories for stereoanyvideo:
Users that are interested in stereoanyvideo are comparing it to the libraries listed below
- Match-Stereo-Videos via Bidirectional Alignment (An update of BiDAStereo)☆78Updated 2 weeks ago
- [CVPR2024] Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion☆117Updated 4 months ago
- [ICRA 2025] PUGS: Zero-shot Physical Understanding with Gaussian Splatting.☆85Updated this week
- The official PyTorch implementation of Diffusion Time-step Curriculum for One Image to 3D Generation (CVPR 2024)☆75Updated 9 months ago
- RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds☆36Updated 3 months ago
- The repository for 'Tri$^{2}$-plane: Volumetric Avatar Reconstruction with Feature Pyramid'☆134Updated 2 months ago
- A Unified Driving World Model for Future Generation and Perception☆85Updated last week
- Text-to-3D Generation by 2D Editing☆61Updated last week
- [ICLR 2025] Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling☆72Updated last month
- hybrid sfm with VIO Pose,RGB and depth data☆52Updated last year
- ☆67Updated last week
- [CoRL2024] Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction☆76Updated 5 months ago
- ☆259Updated last month
- Official Code for “Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling”☆137Updated this week
- Wan2.1 with Controlnet☆85Updated this week
- [NeurIPS2024] MVGamba: Unify 3D Content Generation as State Space Sequence Modeling☆57Updated 3 months ago
- ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding☆137Updated 2 weeks ago
- [CVPR2023] REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos☆270Updated last year
- Official implementation of paper "Multi-Level Collaboration in Model Merging"☆40Updated 2 weeks ago
- Efficient DiT architecture for text2any tasks, ICLR2025☆399Updated last month
- Free-T2M: Frequency enhanced text-to-motion diffusion model with consistency loss☆58Updated last month
- The official implementation of MotionLab☆107Updated 2 weeks ago
- Uncommon Objects in 3D dataset☆1,269Updated last week
- ☆74Updated last week
- Efficient controlnet for DiTs☆65Updated last week
- https://www.kaggle.com/competitions/image-matching-challenge-2022☆44Updated 2 years ago
- GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation☆495Updated last year
- ☆27Updated 4 months ago
- Generating Daylight-driven Architectural Design via Diffusion Models☆22Updated last month
- [🔨software] Sketch-based tree modeling software, implemented in C++ and OpenGL.☆109Updated 2 weeks ago