SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

记录学习Unity Shader过程中实现过的一些Demo。

自定义平滑拖尾

2D类银河恶魔城测试项目

Unity3D开发的第三人称打僵尸生存游戏

cocos2d-x 俯视角丧尸生存2D像素游戏

[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning

A realistic visual–inertial dataset for evaluating SLAM systems in indoor pedestrian-rich environments.

分别使用OpenCV、ONNXRuntime部署YOLOPV2目标检测+可驾驶区域分割+车道线分割，一共包含54个onnx模型，依然是包含C++和Python两个版本的程序。仅仅只依赖OpenCV就能运行，彻底摆脱对任何深度学习框架的依赖。

You Only Look Once for Panopitic Driving Perception.（MIR2022）

CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理和 C++基础四大块，一起努力向offers发起冲击！

7th place solution for the Image Matching Challenge 2023.

Image Matching Challenge (Silver medal solution)

Accurate geometric camera calibration with generic camera models

LightGlue-OnnxRunner is a repository hosts the C++ inference code of LightGlue in ONNX format，supporting end-to-end/decouple model inference of SuperPoint/DISK + LightGlue

C++ implementation of ALIKED feature extractor with LightGlue kepoints matcher

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

Disk code release

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024

A PyTorch implementation of Ellipse R-CNN

PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network (CVPR 2023)

一个基于OpenCV的SFM简单实现，学习用途。欢迎光临我的主页查看更多其他项目详情。