Lists (4)
Stars
Causal video-action world model for generalist robot control
An open-source navigation stack based on Odin1.
【RA-L 2026】 A Robust and Efficient LiDAR-Inertial Odometry System with a Compact Mapping Strategy.
[RA-L] CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAM
[ToG] Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids
🍳 [CVPR'25] PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
GLIM: versatile and extensible point cloud-based 3D localization and mapping framework
[IROS 2024] A 3D Global Descriptor For Loop Closure Detection. NDT-Map-Code.
Original reference implementation of "StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering"
🎤 Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
[CVPR2025] From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
I'm LPR (LiDAR Place Recognition), even if built upon a Vision Foundation Model.
A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)
Reading list for research topics in embodied vision
🐍 Geometric Computer Vision Library for Spatial AI
[IEEE RA-L & ICRA 2026] Semantic-Driven Voxel Representation for LiDAR–Inertial Odometry
This repository aims to bridge the gap between academic research and industrial deployment of 3D Gaussian Splatting (3DGS) technology.
Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
an advanced implementation of the Point-LIO algorithm
Code for RSS'25 paper "MISO: Multiresolution Submap Optimization for Efficient Globally Consistent Neural Implicit Reconstruction"