🔥🔥 Deep Learning Head Pose Estimation using PyTorch.

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Erase specific content from the video that you don't wanna see

Inpaint anything using Segment Anything and inpainting models.

OCR, layout analysis, reading order, table recognition in 90+ languages

Visual studio project for object detection with SIFT features using OpenCV.

[TPAMI'24] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

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

[CVPR 2021] Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach

The libunibreak library

✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

The official rendering library for PAG (Portable Animated Graphics) files that renders After Effects animations natively across multiple platforms.

[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Python library for YOLO small object detection and instance segmentation

APNG、WebP converter

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Image restoration with neural networks but without learning.

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

A unofficial pytorch implementation of PAN(PSENet2): Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

HarfBuzz text shaping engine

Face Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

AI Roadmap:机器学习(Machine Learning)、深度学习(Deep Learning)、对抗神经网络(GAN），图神经网络（GNN），NLP，大数据相关的发展路书(roadmap), 并附海量源码（python，pytorch）带大家消化基本知识点，突破面试，完成从新手到合格工程师的跨越，其中深度学习相关论文附有tensorflow caffe官方源码，应用部分含推荐算法…

Large World Model -- Modeling Text and Video with Millions Context