Stars
3D Object Reconstruction project is a workflow that takes a set of stereo images and camera info and outputs a textured mesh (i.e., .OBJ file). The purpose is to translate physical items into the d…
[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
3D visualization library for rapid prototyping of 3D algorithms
Implementation of paper: Analytic Spherical Harmonic Coefficients for Polygonal Area Lights
CoTracker is a model for tracking any point (pixel) on a video.
A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.
[TPAMI 2025] Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
Official implementation of Continuous 3D Perception Model with Persistent State
Project page of our camera calibration method accepted by ECCV2022
[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth
[NeurIPS 2024] VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
3D Gaussian Splatting (3DGS) on fisheye cameras
Fuse multiple depth frames into a TSDF voxel volume.
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
VGGSfM: Visual Geometry Grounded Deep Structure From Motion
Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.
GPU Accelerated Non-rigid ICP for surface registration
📷 📷 Stereo camera calibration using OpenCV and C++
This is a collective repository for all 3DGS related progresses in research and industry world
(3DV 2025) AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones
[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel