#
Starred repositories
[CSUR 2024] LiDAR-based Place Recognition For Autonomous Driving: A Survey
[ICLR 2024] FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
[Arxiv'24] OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Seman- tic Guidances
56
Updated May 15, 2025
code for "Human-centered design and fabrication of wearable multimodal visual prosthesis"
Source code for the paper "Guarantees for Greedy Maximization of Non-submodular Functions with Applications" in ICML 2017
[ISPRS J] Cross-modal Semantic Transfer for Point Cloud Semantic Segmentation
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging
[IEEE TIP, accepted] This is an official implementation of “Passive Non-Line-of-Sight Imaging Using Optimal Transport” with PyTorch.
Summarize Massive Datasets using Submodular Optimization
NLOST-Non-Line-of-Sight-Imaging-with-Transformer (CVPR2023)
Fully open reproduction of DeepSeek-R1
[ISPRS J 24] Look At the Whole Scene: General Point Cloud Place Recognition by Classification Proxy
Robust Odometry and Mapping for Multi-LiDAR Systems with Online Extrinsic Calibration
[Single/Sparse View-to-Scene on a 4090(24G)] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
🏡 GitHub Pages template for personal academic homepage
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
[ICRA2025] HeLiOS: Heterogeneous LiDAR Place Recognition
Project repo for "A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking"
PyTorch implementation of paper: GaussNav: Gaussian Splatting for Visual Navigation
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
Pointcept: a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral), PPT (CVPR'24), MSC (CVPR'23)
A collection of deep learning based localization models
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
The official implementation of the CVPR'2024 work Interference-Free Low-Rank Adaptation for Continual Learning