Stars
Like "ls", but for images. Shows thumbnails in terminal using sixel graphics.
A lightweight H.265/HEVC intra-frame encoder for grayscale image compression, with only 1600 lines of C. 一个轻量级H.265/HEVC帧内编码器，用于进行灰度图像压缩。代码量仅为1600行C语言，易于理解。
Code release for CVPR'24 submission 'OmniGlue'
🤩 An AWESOME Curated List of Papers, Workshops, Datasets, and Challenges from CVPR 2024
Training library for local feature detection and matching
YOLOv10: Real-Time End-to-End Object Detection
Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
Public implementation of "Beyond Cartesian Representations for Local Descriptors", ICCV 2019
Count the MACs / FLOPs of your PyTorch model.
Dense Distinct Query for End-to-End Object Detection (CVPR2023)
[CVPR 2024] Neural Markov Random Field for Stereo Matching
Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching
OpenMMLab Rotated Object Detection Toolbox and Benchmark
Detailed comments for ORB-SLAM3
Detailed comments for ORB-SLAM2 with trouble-shooting, key formula derivation, and diagrammatic drawing
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Implementation of "Learning to Match Features with Seeded Graph Matching Network" ICCV2021
Code for "Detector-Free Structure from Motion", CVPR 2024
The official GitHub page for the survey paper "A Survey of Large Language Models".
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
Implementation of the paper "DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients"
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching