AD-Census立体匹配算法，中国学者Xing Mei等人研究成果（Respect！），算法效率高、效果出色，适合硬件加速，Intel RealSense D400 Stereo模块算法。完整实现，代码规范，注释清晰！

Source codes collection for 3d vision 视觉三维重建领域的源码收集

这是一个基于CUDA加速的SGM立体匹配代码，它的核心是SemiglobalMatching（SGM）算法，它不仅在时间效率上要远远优于基于CPU的常规SGM，而且明显占用更少的内存，这意味着它不仅可以在较低分辨率（百万级）图像上达到实时的帧率，且完全具备处理千万级甚至更高量级图像的能力。

《立体视觉入门指南》 代码， c++ code for StereoV3D course

PatchMatchStereo，倾斜窗口经典，效果极佳，OpenMVS&Colmap稠密匹配算法。完整实现，代码规范，注释清晰，博客教学！

SGM，立体匹配StereoMatching最经典应用最广泛算法，4000+引用，兼顾效率和效果。完整实现，代码规范，注释清晰，博客教学！

Mirror of Visualization Toolkit repository

C++ Library Manager for Windows, Linux, and MacOS

Markdown version of the Visualization Toolkit Book - An object Oriented Approach to 3D Graphics

A C++ library for interacting with JSON.

spdlog简单封装

Fast C++ logging library.

cuda version of the Discrete Fourier treansform

Repository for OpenCV's extra modules

GDAL is an open source MIT licensed translator library for raster and vector geospatial data formats.

DO NOT CHECK OUT THESE FILES FROM GITHUB UNLESS YOU KNOW WHAT YOU ARE DOING. (See below.)

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

OpenMMLab Model Deployment Framework

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

🤘 awesome-semantic-segmentation

使用pytorch_quantization对yolov8进行量化

yolov8 瑞芯微 rknn 板端 C++部署。

YOLOv8-pose implementation using PyTorch

YOLOv8-3D is a LowCode, Simple 2D and 3D Bounding Box Object Detection and Tracking , Python 3.10

yolov8 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

这是一个yolov8-pytorch的仓库，可以用于训练自己的数据集。