[CVPR2025] LightLoc: Learning Outdoor LiDAR Localization at Light Speed

Gradient, divergence, Laplacian on point clouds. Useful for setting up and solving PDEs on point clouds and learning anisotropic features in deep learning.

This is the official GitHub page of the Multi-Spectral Stereo (MS2) dataset described in CVPR 2023 paper.

The codes for CVPR2024 paper 'Text2Loc: 3D Point Cloud Localization from Natural Language'

[RSS 2025] GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction

[T-RO'25] HiMo: High-Speed Objects Motion Compensation in Point Clouds

PRIOR-SLAM: Enabling Visual SLAM for Loop Closure under Large Viewpoint Variations

Official PyTorch Implementation of Revisiting Self-Similarity: Structural Embedding for Image Retrieval, CVPR 2023

The official repository for ScalableMap (CoRL 2023)

CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition -- ICCV 2023

[ICLR 2025] NextBestPath: Efficient 3D Mapping of Unseen Environments

[RA-L'25] CLID-SLAM: A Coupled LiDAR-Inertial Neural Implicit Dense SLAM with Region-Specific SDF Estimation

[Arxiv'24] OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Seman- tic Guidances

Toolkit for localization evaluation with CSV/ROS 2 bag support, error analysis, and NDT performance metrics.

[CoRL 2025] ActLoc: Learning to Localize on the Move via Active Viewpoint Selection

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

SOTA SONAR Global Descriptor in Underwater SONAR Place Recognition (accepted in ICRA'23)

Segment This Thing is an efficient image segmentation models that uses a biologically-inspired foveated tokenization to reduce inference costs.

[2025 CoRL] ScrewSplat: An End-to-End Method for Articulated Object Recognition

[T-RO 2025] Scalable Lidar-Visual NeRF

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

I'm LPR (LiDAR Place Recognition), even if built upon a Vision Foundation Model.

[IEEE IROS'25] GSPR: Multimodal Place Recognition using 3D Gaussian Splatting for Autonomous Driving

Pyramid Point Cloud Transformer for Large-Scale Place Recognition

Riemannian Optimization for Active Mapping with Robot Teams (ROAM)

Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information

Diffusion-based Tree Skeletonization

Official repository for the NeurIPS 2024 paper "SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition".