Official Implementation of "PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting"

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

DUSt3R: Geometric 3D Vision Made Easy

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

OpenXRLab Multi-view Motion Capture Toolbox and Benchmark

Make human motion capture easier.

OpenMMLab Pose Estimation Toolbox and Benchmark.

A collection of awesome resources in Human Pose estimation.

Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"

Official code for "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation"

Code for "Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo"

Official implementation of Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

code for cvpr2020 "4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras"

Code for "Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views" (CVPR 2019, T-PAMI 2021)

NeurIPS-2021: Direct Multi-view Multi-person 3D Human Pose Estimation

[ICCV2021] Code Release of Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".

Trim 3D Gaussian Splatting for Accurate Geometry Representation

[ECCV 2024] Official implementation of the paper "GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views"

DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

The official implementation for the paper “Quadratic Gaussian Splatting for Efficient and Detailed Surface Reconstruction.”

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

This repository contains the code for the paper An Efficient 3D Gaussian Representation for Monocular/Multi-view Dynamic Scenes https://arxiv.org/abs/2311.12897

(ECCV '24) DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

Simple Viser Viewer for 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

[NeurIPS 2024] Geometry-Aware Large Reconstruction Model for Efficient and High-Quality 3D Generation

[NeurIPS 2024] VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction

[NeurIPS'24] Official implementation of "HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors"