ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction

[CVPR 2025] AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

The official implementation of "TVG-SLAM: Robust Gaussian Splatting SLAM with Tri-view Geometric Constraints"

[ICIP2024] Real-time Monocular Depth Estimation on Embedded Systems

基于LK光流法代替ORB-SLAM2中的特征点提取匹配法来跟踪关键点

Efficient Incremental BA

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

[3DV 2025] Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

Lite Any Stereo: Efficient Zero-Shot Stereo Matching

Official implement of VGGT-Long

[ICCV'25] 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

A deep learning-powered RGB-D SLAM framework leveraging SuperPoint for feature extraction and LightGlue for feature matching, enhancing localization accuracy.

Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.

Ground-Fusion++: a modular sensor-fusion SLAM system(IROS2025)

Official code for the paper: Depth Anything At Any Condition

Depth Anything 3

CVPR2024 论文EdgePoints C++复现

Official implementation of "MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation"

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

[CVPR 2025] MINIMA: Modality Invariant Image Matching

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

🚀 Kick-start your C++! A template for modern C++ projects using CMake, CI, code coverage, clang-format, reproducible dependency management and much more.

Code of π^3: Permutation-Equivariant Visual Geometry Learning

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

ComfyUI nodes for Lotus depth/normal prediction

EdgePoint: Learning Efficient Keypoint Extraction and Description for Edge Devices