Starred repositories
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音,一键全自动视频搬运AI字幕组
Multi-Joint dynamics with Contact. A general purpose physics simulator.
A generative world for general-purpose robotics & embodied AI learning.
Industry leading face manipulation platform
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
A collection of papers on neural field-based inverse rendering.
The official repo for "SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars"
High-resolution models for human tasks.
[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"
CoTracker is a model for tracking any point (pixel) on a video.
Implementation of "Large Steps in Inverse Rendering of Geometry"
Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024
NIST FRVT top ranked Face recognition SDK Android with 3D passive face liveness detection: face recognition by face matching, face compare, face comparison, face identification, face anti-spoofing,…
This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]
MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR2024 Oral)
Official Pytorch Implementation of SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024)
Fitting 3DMM models to multiview (monocular) video data.
[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models
Dynamic Gaussian Mesh: Consistent Mesh Reconstruction from Monocular Videos
Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]
Learning Disentangled Avatars with Hybrid 3D Representations. (Face, Body, Hair and Clothing)
Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance (ICCV2023)
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code