Stars
[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
Seen2Scene takes an incomplete real-world 3D scan and generates a complete, coherent 3D scene using visibility-guided flow matching — trained directly on real-world data.
4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video
Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.
A toolbox for target-less LiDAR-camera calibration [ROS1/ROS2]
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
Describe Anything, Anywhere, at Any Moment (DAAAM), a novel approach to real-time, large-scale, spatio-temporal memory
[ICLR'26] YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
Official implementation of "Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation".
Convert 360° equirectangular panoramas into viewable 3D Gaussian Splat files.
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
A Handy Extrinsic Calibration Tool for LiDAR-camera Systems.
High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
Native and Compact Structured Latents for 3D Generation
The official repository for Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries
[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking
MaterialX is an open standard for the exchange of rich material and look-development content across applications and renderers.
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…