[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

This is a unofficial fork of OpenVSLAM (https://github.com/xdspacelab/openvslam)

Python implementation of Visual Odometry algorithms from http://rpg.ifi.uzh.ch/

A Robust and Versatile Monocular Visual-Inertial State Estimator

Infinitesimal Plane-based Pose Estimation (IPPE): A very fast method to compute a camera's pose from a view of a planar object

3D Gaussian Splatting (3DGS) on fisheye cameras

🔥(CVPR 2023) ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction

[ECCV'24] 3D Hand Pose Estimation in Everyday Egocentric Images

High-resolution models for human tasks.

ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild"

Halpe: full body human pose estimation and human-object interaction detection dataset

SynthMoCap Datasets

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

#1 Open Source Unity Networking Library

Code of "NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation", CVPR 2023

C++ implementation of Lie Groups using Eigen.

Metric depth estimation from a single image

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

real time face swap and one-click video deepfake with only a single image

This repository contains utilities for loading data from Meta's datasets with hand pose annotations, computing hand tracking metrics, and visualising results of a hand tracking method.

UmeTrack Unified multi-view end-to-end hand tracking for VR

HOT3D: An egocentric dataset for 3D hand and object tracking

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

A collection of papers on diffusion models for 3D generation.

An experimental 3D Gaussian Splat viewer written in Rust (CPU rendering)