High-Resolution 3D Human Digitization from A Single Image.

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

Depth-Aware Video Frame Interpolation (CVPR 2019)

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models

🔥 2D and 3D Face alignment library build using pytorch

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Real-Time High-Resolution Background Matting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

OpenMMLab Pose Estimation Toolbox and Benchmark.

Official repo for consistency models.

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

TripoSR: Fast 3D Object Reconstruction from a Single Image

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

PyTorch ,ONNX and TensorRT implementation of YOLOv4

StyleGAN2-ADA - Official PyTorch implementation

LPIPS metric. pip install lpips

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Efficient 3D human pose estimation in video using 2D keypoint trajectories

Free Motion Capture for Everyone 💀✨

T2I-Adapter