Stars
[CVPR 2025] DEFOM-Stereo: Depth foundation model based stereo matching
OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline
Stereo Algorithms (Include:CREStereo,RAFT-Stereo,Hitnet,FastACVNet_plus,Stereo Transformers,RealtimeStereo,DistDepth) with TensorRT,ORT,OpenVINO
Part of my final year project: "Robot Path Planning based on Visual SLAM". This is the Visual SLAM part. This project is mainly based on https://github.com/lturing/ORB_SLAM3_ROS
This code is an extended version of YOLO_ORB_SLAM3, which adds the functionality of creating dense point cloud maps.
Code and data for "SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation"
YOLOv8-ROS-TensorRT-CPP detect, segment & pose including ros1 & ros2.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022
A modified C++ wrapper for Segment Anything, MobileSAM, HQ-SAM, and EdgeSAM models, adapted for seamless integration with iOS applications, offering pure C++ inference with no Python dependencies.
Gaussian Splatting implementation based on gsplat. Easy to install and use.
Ongoing research training gaussian splatting at scale by distributed system
Official repository of the 3DV 2025 paper "LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming"
Extensions for diff-gaussian-rasterization, with depth forward and backward pass, and 4th SH degree
😎 GsplatLoc 🎯: Ultra-Precise Pose Optimization via 3D Gaussian Reprojection 🌟
[ECCV 2024] SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
A comprehensive list of Implicit Representations, NeRF and 3D Gaussian Splatting papers relating to SLAM/Robotics domain, including papers, videos, codes, and related websites
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
[ICML 2021] Self-supervised pre-training of AI models on ECG data with CLOCS