SpatialVision / Orient-Anything-V2Links
Orient Anything V2, NeurIPS 2025 Spotlight
☆118Updated last month
Alternatives and similar repositories for Orient-Anything-V2
Users that are interested in Orient-Anything-V2 are comparing it to the libraries listed below
Sorting:
- [CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video☆218Updated 7 months ago
- [CVPR2025] Official Implementation of AuraFusion360☆79Updated 6 months ago
- Code for "BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation", ICCV 2025.☆100Updated 3 months ago
- An unified model for 4D human-scene reconstruction☆424Updated 2 weeks ago
- ☆67Updated 2 weeks ago
- Official Implementation of paper "St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World"☆101Updated 3 months ago
- Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video☆33Updated last week
- ☆269Updated 2 months ago
- Trace Anything: Representing Any Video in 4D via Trajectory Fields☆456Updated 2 months ago
- [arXiv 2025] Generative View Stitching☆99Updated 2 months ago
- [ICCV 2025] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis☆105Updated 2 months ago
- [AAAI 2026] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting☆71Updated this week
- ☆123Updated 6 months ago
- [arXiv'25]🌈 Unseen 3D Geometry Reasoning from a Single Image.☆73Updated 6 months ago
- [ CVPR 2025 ] We introduce LT3SD, a novel latent 3D scene diffusion approach enabling high-fidelity generation of infinite 3D environment…☆188Updated 2 months ago
- Fillerbuster: Multi-View Scene Completion for Casual Captures☆110Updated 11 months ago
- [NeurIPS 2024] Geometry-Aware Large Reconstruction Model for Efficient and High-Quality 3D Generation☆172Updated last year
- [NeurIPS 2024] DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos☆231Updated last year
- ☆90Updated last year
- "E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.☆226Updated 2 weeks ago
- [SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes☆160Updated last month
- [CVPR 2025] GenFusion: Closing the Loop between Reconstruction and Generation via Videos☆155Updated 8 months ago
- PhyRecon: Physically Plausible Neural Scene Reconstruction☆175Updated 9 months ago
- ☆104Updated 4 months ago
- [CVPR2025] Feat2GS: Probing Visual Foundation Models with Gaussian Splatting☆228Updated 5 months ago
- IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction☆314Updated last month
- VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control☆44Updated last week
- [CVPR 2025] Official code for the paper "SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis"☆130Updated 9 months ago
- Code release for the paper "ShowMak3r: Compositional TV Show Reconstruction" (CVPR 2025)☆89Updated 10 months ago
- MEt3R: Measuring Multi-View Consistency in Generated Images☆147Updated 5 months ago