Starred repositories
Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
Vayuvahana Technologies Private Limited presents to you VajraV1, a state-of-the-art (SOTA) real time object detection model
This project is the official implementation of "UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation"
🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.
The code for PixelRefer & VideoRefer
Production First and Production Ready End-to-End Speech Recognition Toolkit
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
A GPU-accelerated library that enables random frame access and efficient video decoding for data loading.
Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"
Official repo for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations, ECCV 2024
FastTracker: Real-Time and Accurate Visual Tracking
Goliath Dataset and Official PyTorch Implementation of RelightableHands, Relightable Gaussian Codec Avatars, and Driving-Signal Aware Full-Body Avatars.
Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton…
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…
[WACV 2026] SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering
[ICLR 2025] SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training
The official implementation of SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation
A modern download manager that supports all platforms. Built with Golang and Flutter.
Make Your Training Flexible: Towards Deployment-Efficient Video Models