Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

[RA-L'25] An Reliable and Efficient Framework for Zero-Shot Object Navigation

RealSee3D: A multi-view RGB-D dataset combining real-world captures and procedurally generated scenes, with extensible annotations for diverse 3D vision research.

Deep Reinforcement Learning

Open source SDK to create applications leveraging event-based vision hardware equipment

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…

SAM 3D Objects

Pose-only SDK for Structure from Motion

Isaac Gym Environments for Legged Robots

Lidar Localization and Mapping

Building General-Purpose Robots Based on Embodied Foundation Model

[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"

SLAM-Former: Putting SLAM into One Transformer

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

Monocular Lane Detection Based on Deep Learning: A Survey

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

InternRobotics' open platform for building generalized navigation foundation models.

Official implementation of NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments (ICCV'25).

Embodied Instruction Following in Unknown Environments

[3DV 2026] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

Official Repo of "SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization"

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

对VINS-Fusion的修改，以适配地面小车进行定位建图及导航，可实时采集生成半稠密点云地图和栅格地图。

ROS2 version of VINS-Fusion

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

Fast Incremental Euclidean Distance Fields for Online Motion Planning of Aerial Robots

Python scraper based on AI

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged Robotics

MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)