Code for Faster VGGT with Block-Sparse Global Attention
☆89Nov 14, 2025Updated 3 months ago
Alternatives and similar repositories for sparse-vggt
Users that are interested in sparse-vggt are comparing it to the libraries listed below
Sorting:
- [CVPR 2025] "DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion" official implementation.☆182Jul 7, 2025Updated 8 months ago
- [CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations☆504Updated this week
- [arXiv'25]🌈 Unseen 3D Geometry Reasoning from a Single Image.☆76Jul 10, 2025Updated 7 months ago
- Official code for paper: "RayRoPE: Projective Ray Positional Encoding for Multi-view Attention"☆106Feb 25, 2026Updated last week
- ☆18Jan 2, 2024Updated 2 years ago
- Official repository of the CVPR24 paper "The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement"☆57Aug 10, 2024Updated last year
- ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation☆478Jan 27, 2026Updated last month
- [ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.☆513Apr 1, 2025Updated 11 months ago
- NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization, CVPR2023☆65Nov 16, 2023Updated 2 years ago
- [Arxiv'25] SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images☆46Oct 18, 2025Updated 4 months ago
- [CVPR 2025] GenFusion: Closing the Loop between Reconstruction and Generation via Videos☆163Apr 22, 2025Updated 10 months ago
- Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)☆292May 7, 2025Updated 9 months ago
- [CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affin…☆231Apr 8, 2025Updated 10 months ago
- [WACV 2025] Official code of "SEED4D: A Synthetic Ego-Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark"☆21Sep 3, 2025Updated 6 months ago
- This code is for align lidar points with COLMAP sparse point cloud. The code is an official implementation of GauUScene.☆40Jun 2, 2024Updated last year
- Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) …☆127Oct 22, 2025Updated 4 months ago
- [SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views☆744Dec 22, 2025Updated 2 months ago
- ☆39Mar 19, 2025Updated 11 months ago
- ☆124Jun 17, 2025Updated 8 months ago
- [ICML 2024] Scale-Free Image Keypoints Using Differentiable Persistent Homology☆11May 5, 2024Updated last year
- Gaussian Splatting from VGGSfM and Mast3r, and their comparison☆228Aug 23, 2024Updated last year
- [NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory☆179Sep 26, 2025Updated 5 months ago
- ☆281Feb 3, 2026Updated last month
- ICCV 2023 Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors☆16Jun 30, 2024Updated last year
- ☆25Jun 20, 2025Updated 8 months ago
- A simple state update rule to enhance length generalization for CUT3R☆595Oct 1, 2025Updated 5 months ago
- [NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats☆519Oct 14, 2025Updated 4 months ago
- [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer☆691Jan 28, 2026Updated last month
- [NeurIPS 2025 Official Codes] Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards☆44Sep 23, 2025Updated 5 months ago
- [ECCV 2024] SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction☆187Sep 18, 2024Updated last year
- A Unified Perspective-to-Equirectangular Visual Place Recognition Framework☆19Dec 19, 2025Updated 2 months ago
- A confidence-aware depth-based optimization strategy for 3D Gaussian Splatting (3DGS).☆47Sep 23, 2025Updated 5 months ago
- Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data (CVPR 2025)☆199May 20, 2025Updated 9 months ago
- VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders☆86Nov 5, 2025Updated 4 months ago
- [ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models☆119Jan 23, 2026Updated last month
- [CVPR'26] Official implementation of "C3G: Learning Compact 3D Representations with 2K Gaussians"☆147Feb 24, 2026Updated last week
- ☆123Apr 18, 2025Updated 10 months ago
- Official code for VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator☆112Feb 16, 2026Updated 2 weeks ago
- (ECCV2024) KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter☆19Jun 27, 2025Updated 8 months ago