Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
- image-enhancement
- image-processing
- computer-vision
- deep-learning
91,851 visible repositories in the index
481–504 of 847 · Most stars
Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
微博爬虫及配套工具箱,微博用户、话题、评论采集一网打尽。图片下载、情感分析,地理位置、关系网络、spammer 机器人识别等功能应有尽有。Docs:https://buyixiao.github.io/blog/weibo-super-spider.html 配套可视化网站:https://buyixiao.github.io/blog/one-stop-weibo-visualization.html
Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
Masked Depth Modeling for Spatial Perception
Google, Naver multiprocess image web crawler (Selenium)
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
Extract one time password (OTP) secrets from QR codes exported by two-factor authentication (2FA) apps such as "Google Authenticator". The exported QR codes from authentication apps can be captured by camera, read from images, or read from text files. The secrets can be exported to JSON or CSV, or printed as QR codes to console.
[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two
A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.
A state-of-the-art semi-supervised method for image recognition
Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more.
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
A fast, efficient universal vector embedding utility package.
Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?
自然语言驱动的无限画布工作流 Agent,让 AI 视频创作第一次真正变成可编辑的工作流。 AICON 面向创作者,提供从剧本拆解、分镜生成、素材生成、视频合成到内容分发的一整套能力。 不是只给你一个输入框,而是让你用自然语言和无限画布一起驱动创作,把文本、图片、视频节点组织成完整链路,真正把“从灵感到 成片”放进一个系统里完成。
[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency