[NeurIPS 2025] Pixel-Perfect Depth

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

✯ 可直连访问的电视/广播图标库与相关工具项目 ✯ 🔕 永久免费 直连访问 完整开源 不断完善的台标 支持IPv4/IPv6双栈访问 🔕

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

A Python package for fast and robust Image Stitching

The official generation code and toolkits of VDW dataset (ICCV 2023)

[CVPR 2024 Highlight] Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

Simple DepthAnythingV2 inference node for monocular depth estimation

[CVPR 2024 - Oral] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Effortlessly deploy CREStereo in PyTorch with a simple pip install.

Home Assistant integration for Haier hOn: support for Haier/Candy/Hoover home appliances like washing machines and air conditioners in 19 languages.

😎 Finding duplicate images made easy!

TVBox保存源

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

[Does not work anymore!] Script to enable systemd support on current Ubuntu WSL2 images

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…

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Focus on prompting and generating

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Yolov5 Face Detection

yolov7 face detection with landmark

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.

[CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching and Multi-View Stereo

[CVPR 2023] Rethinking Optical Flow from Geometric Matching Consistent Perspective