A feed-forward 3D foundation model for reconstructing scenes from streaming data

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

LLM powered Sublime Text plugin to autocomplete inline code

InSAR Scientific Computing Environment version 2

Release repo for our SLAM Handbook

Using SNAP as InSAR processor for StaMPS

AlphaGo Moment for Model Architecture Discovery.

MapLibre GL JS - Interactive vector tile maps in the browser

Datasets to protect Earth's forests and biodiversity

GeeFlow - generate and process large-scale geospatial datasets with Google Earth Engine.

Jeo: Jax model training lib for Earth Observation

WarpDrive is an S3-ish rocket engine optimised for ML/Database workloads but also general purpose

An One-Click Autodesk Fusion script to convert a robot model to a ready to use ROS2 package,

[T-RO 24] Swarm-LIO2: Decentralized, Efficient LiDAR-inertial Odometry for UAV Swarms

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

Grounding Image Matching in 3D with MASt3R

🍃 Organic Maps is a free Android & iOS offline maps app for more than 6M travelers, tourists, hikers, and cyclists. It uses crowd-sourced OpenStreetMap data and is developed with love by the commun…

Wan: Open and Advanced Large-Scale Video Generative Models

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Maybe the first academic open work on stereo 3D SSC method with vision-only input.

A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.

This project focuses on harnessing the power of Pseudo-LiDARs and 3D computer vision for unmanned aerial vehicles (UAVs). By integrating Pseudo-LiDAR technology with Stereo Global Matching (SGBM) a…

With Stereo Vision, 3D reconstruction based on two methods. First, correlation based algorithm which extracts disparity map then estimate depth value. The other is Feature-based algorithm which ext…

This project accomplishes the task of 3D reconstruction based on binocular stereo vision. It realizes the entire process from camera calibration, image matching, to point cloud visualization.

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

The official repo for [JSTARS'24] "MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining"

Repository for the paper "Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes"