Realcat

cv-arxiv-daily. 🎓Automatically Update CV Papers Daily using Github Actions

image-matching-webui. 🤗 image matching webui

Recent-Stars-2025. 🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

LineSegmentsDetection. 📐A collection of line segments detection algorithms.

colmap-gps. 🌟 COLMAP + GPS Prior

Depth-Estimation-Light-Field. 👾 A collection of code of depth estimation using light field data.

ORB-SLAM2-CHINESE. 🚀中文注释版ORB-SLAM2

light-field-Processing. :baby_chick:This is an useful tool to decode/display lightfield files(.lfp) OR 2D remapping images into 5D data.

omniglue-onnx. ONNX-compatible OmniGlue: Generalizable Feature Matching with Foundation Model Guidance

colmap-rerun. Simple tool to visualize COLMAP sparse/dense reconstruction using Rerun.

depth-from-defocus-and-correspondence. :snowman:Depth from Combining Defocus and Correspondence Using Light-Field Cameras.

light-field-TB. :apple:This is a simple test for light field ToolBox.

omni-sfm. Structure-from-Motion pipeline for omnidirectional imagery

RoMa. [CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

Light-Field-Refocusing. :watermelon:This is a demo of light field refocusing

Optimal-Transport. 🦆 A simple sinkhorn algorithm to solve optimal transport problem writen in Matlab

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

background-bokeh. :smile:Blur background using depth map and color image.

fire. Learning Super-Features for Image Retrieval

youtube-dl-webui. youtube video downloader webui

Thermal_SuperPoint_SLAM. Codebase for training a thermal SuperPoint network and vocabulary and integrating them with ORB-SLAM2

COTR. Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)

camera2_demo. 本项目使用Camera2 API实现相机图像实时预览与连续图像保存。

mpsfm. MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)

transformer-explainer. Transformer Explained: Learn How Transformer Models Work with Interactive Visualization

Superglue-with-Physarum-Dynamics. This repository contains the implementation of SuperGlue with Physarum Dynamics LP solver.

VisualSuperPose. C++

OpenGlue. Open Source Graph Neural Net Based Pipeline for Image Matching

AI-Expert-Roadmap. Roadmap to becoming an Artificial Intelligence Expert in 2022

ml-fastvlm. This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

vipe. ViPE: Video Pose Engine for Geometric 3D Perception

SuperPoint-Pytorch. Pytorch Implementation of rpautrat/SuperPoint

TopicFM. [AAAI-23] TopicFM: Robust and Interpretable Topic-Assisted Feature Matching

pr-automator. 🤖 AI-powered PR description generator with multi-provider support

ml-aspanformer. used in hloc project, link below

PoseLib. Minimal solvers for calibrated camera pose estimation

DKM. [CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

Hierarchical-Localization. Visual localization made easy with hloc

llm-viz. 3D Visualization of an GPT-style LLM