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

Torchreid: Deep learning person re-identification in PyTorch.

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

An experimental HTML5 & WebGL video composition and rendering API.

Code release for NeRF (Neural Radiance Fields)

Learn OpenCV 4 By Building Projects, Second Edition, published by Packt

Slick, declarative command line video editing

Python library to convert CSS animations into video

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose"

TensorFlow code and pre-trained models for BERT

The GL Vendor-Neutral Dispatch library

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

An open source library for face detection in images. The face detection speed can reach 1000FPS.

Research platform for 3D object detection in PyTorch.

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

Deezer source separation library including pretrained models.

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions

An Open Source Machine Learning Framework for Everyone

🎥 Python and OpenCV-based scene cut/transition detection program & library.

Official Pytorch implementation of Copy-and-Paste Networks for Deep Video Inpainting (ICCV 2019)

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

Implementation of the paper: Text Segmentation as a Supervised Learning Task

Just draw a bounding box and you can remove the object you want to remove.

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

移动端快速视频人脸跟踪-移动端150FPS+

Deepfakes Software For All

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Implementation of the paper 'Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks' from scratch.