Text recognition (optical character recognition) with deep learning methods, ICCV 2019
- iccv2019
- ocr
- ocr-recognition
- text-recognition
66,263 visible repositories in the index
25–48 of 121 · Most stars
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Farbrausch demo tools 2001-2011
A procedural Blender pipeline for photorealistic training image generation
OpenSceneGraph git repository
List of Dirty, Naughty, Obscene, and Otherwise Bad Words
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
IPED Digital Forensic Tool. It is an open source software that can be used to process and analyze digital evidence, often seized at crime scenes by law enforcement or in a corporate investigation by private examiners.
Godot engine addon to randomly fill an area with props or other scenes. Mirror of https://codeberg.org/hungryproton/proton_scatter
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
End-to-end Chinese scene-text detection and recognition with CTPN, CRNN, and CTC (legacy project).
Personal portfolio website with interactive animations and visual storytelling. Built with React, featuring modular scene management, comprehensive testing, and smooth cross-device performance.
The devkit of the nuScenes dataset.
🎬 Scene.js is JavaScript & CSS timeline-based animation library
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
A basic 3D scene implemented with various engines, frameworks or APIs.
Open source previs software in the browser: block a scene, pose characters, author camera moves and cuts, then take the same shots to an AI video model.
Godot template with a main menu, options menus, pause menu, credits, scene loader, extra tools, and an example game scene.
World's first general purpose 3D object detection codebse.
GPU-powered 3D HTML. ✨🧊 <lume-box size="1 2 3">
Kotlin extensions for the libGDX game framework
Wallpaper Engine wallpapers on your Mac. A free, open-source app that plays scene, video and web wallpapers from the Steam Workshop. Apple silicon, macOS 15+.
Human Pose Estimation Related Publication
Crinkler is an executable file compressor (or rather, a compressing linker) for compressing small 32-bit Windows demoscene executables. As of 2026, it is the most widely used tool for compressing 1k/4k/8k intros.