A synthetic data generator for text recognition

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

OpenMMLab Model Deployment Framework

最好用的 V2Ray 一键安装脚本 & 管理脚本

RTX HDR modded into MPC-VideoRenderer.

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

3rd party dependencies for DALI project

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

OpenMMLab Image and Video Restoration, Editing and Generation Toolbox

微信云托管 flask 框架模板

Segmentation models with pretrained backbones. PyTorch.

Integrated MLU-accelerated video processing into ffmpeg on Ubuntu/Centos

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

OpenMMLab Foundational Library for Training Deep Learning Models

OpenMMLab Computer Vision Foundation

VRT: A Video Restoration Transformer (official repository)

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

A hybrid neural representation for videos

OpenMMLab optical flow toolbox and benchmark

[CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas

Recurrent Video Restoration Transformer with Guided Deformable Attention (NeurlPS2022, official repository)

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

Towards Unified Keyframe Propagation Models

[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

PlayCover is a project that allows you to sideload iOS apps on macOS (currently arm, Intel support will be tested)

a lightweight, multi-platform, multi-architecture hook framework.

[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting

Watch, fake or block requests from puppeteer matching patterns