Edit gaussian splatting models

Autonomous Exploration, Construction and Update of Semantic Map in real-time

Open-source Multi-agent Poster Generation from Papers

fork from 4DGS

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

SORT3D, an LLM-based object-centric grounding and indoor navigation system employing a spatial reasoning toolbox and state of the art 2D VLMs for perception.

A high-performance C++ header and application for real-time metric depth estimation, using models from Depth-Anything-V2. Powered by ONNX Runtime and OpenCV, it supports seamless inference for imag…

SpatialLM: Large Language Model for Spatial Understanding

YOLOE: Real-Time Seeing Anything

ILIAS: Instance-Level Image retrieval At Scale

A ROS driver for Insta360 cameras, enabling real-time image capture, processing, and publishing in ROS environments.

Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"

[RA-L 2025] The official repository for Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers

3D 场景理解(fork)

MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25

Official implementation of Continuous 3D Perception Model with Persistent State

The full_linear_wheel_odometry_factor provides motion constraints and online calibration for skid-steering robots. This constraint can be incorporated into your SLAM framework. Here is an example v…

Ros2 Package for Using PCL to Convert Point Cloud Data into a Depth Map for Object Detection and Localization

Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians

Web-based 3D visualization + Python

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

BoQ: A Place is Worth a Bag of learnable Queries (CVPR 2024)

A C++ header-only Eigen-based Library for equivariant Inertial Measurement Unit (IMU) preintegration