Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

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

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

[ICCV 2021] Instances as Queries

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, e…

ICCV 2019, Hand Detection

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

Official Code for Towards High Fidelity Face Relighting with Realistic Shadows (CVPR 2021)

A curated list of papers, code and resources pertaining to image composition, including image blending, image harmonization, shadow generation, and object placement.

A Trimap-Free Solution for Portrait Matting in Real Time

RT-GENE: Real-Time Eye Gaze and Blink Estimation in Natural Environments

[ECCV2020] A Large-Scale Face Anti-Spoofing Dataset

Code for 2nd Place Solution in Face Anti-spoofing Attack Detection Challenge @ CVPR2019

手部21个关键点检测，二维手势姿态，手势识别，pytorch,handpose

手部21个关键点检测，二维手势姿态，手势识别，pytorch,handpose

This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 1.8mb and run 97FPS on cellphone🔥

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

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

人像卡通化探索项目 (photo-to-cartoon translation project)

Official Tensorflow Implementation of SATRN (CVPR Workshop WTDDLE 2020)

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

🍅 移动端部署，支持YOLOv5s、YOLOv4-tiny、MobileNetV2-YOLOv3-nano、Simple-Pose与Yolact模型，支持iOS、Android，使用NCNN框架。

Implementation of Our ECCV2020-work: Improving Semantic Segmentation viaDecoupled Body and Edge Supervision

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai

OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark

OpenMMLab Semantic Segmentation Toolbox and Benchmark.