Stars
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
Digital Human Resource: 2D/3D/4D Human Modeling, Avatar Generation & Animation, Clothed People Digitalization, Virtual Try-On, and Others.
This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
A synthetic data generator for text recognition
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
[ECCV 2020] Reimplementation of 3DDFAv2, including face mesh, head pose, landmarks, and more.
This repo is the codebase for our team to participate in DOTA related competitions, including rotation and horizontal detection.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Safety helmet wearing detect dataset, with pretrained model
This is a repository about PCB defect detection.
Lists the papers related to imbalance problems in object detection [TPAMI]
[CVPR 2020] CenterMask : Real-Time Anchor-Free Instance Segmentation
An unofficial PyTorch implementation of VoxelMorph- An unsupervised 3D deformable image registration method
多标签分类,端到端的中文车牌识别基于mxnet, End-to-End Chinese plate recognition base on mxnet
静默活体检测（Silent-Face-Anti-Spoofing）
This is the project page for veri dataset which is a large scale image dataset for vehicle re-identification in urban traffic surveillance.
collection of dataset&paper&code on Vehicle Re-Identification
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"
Four landmark detection algorithms, implemented in PyTorch.
A flexible, effective and fast cross-view gait recognition network