This repository is an implementation of the NeurIPS 2024 paper "LoD-Loc: Visual Localization using LoD 3D Map with Neural Wireframe Alignment".

Repository for paper "SA-GS: Season-Aware Affine 3D Gaussian Splatting for Satellite Image Rendering"

The software toolkits we developed for our paper in ACM CHI 2024.

Windows下基于openMVG+openMVS的三维重建解决方案以及基于Qt的可视化桌面平台

🎓Automatically Update 3DV Papers Daily using Github Actions

🎓Automatically Update CV Papers Daily using Github Actions

Official implementation for paper "Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation" (Pattern Recognition)

This code is for align lidar points with COLMAP sparse point cloud. The code is an official implementation of GauUScene.

📚 A collection of sketch based application papers.

[TPAMI 2026] Interacted Planes Reveal 3D Line Mapping

An Open Framework for Architectural Caption and Attribute Data Enrichment via Street View Imagery

📚 A collection of sketch based application papers.

Deep Sketch-Based 3D Modeling: A Survey

The repository for Eurographics 2026 paper "LeafFit: Plant Assets Creation from 3D Gaussian Splatting"

Official electron build of draw.io

Training code for "Radiance Meshes for Volumetric Reconstruction".

Offical implementation of CVPR 2026 paper SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving.

This repository stores the codes and dataset links for LiteGE - Lightweight Representation for Geodesic Regression and Non-Isometric Shape Matching (AAAI 2026)

Xbotics 社区具身智能学习指南：我们把“具身综述→学习路线→仿真学习→开源实物→人物访谈→公司图谱”串起来，帮助新手和实战者快速定位路径、落地项目与参与开源。

Code for "AutoRecon: Automated 3D Object Discovery and Reconstruction" CVPR 2023 (Highlight)

This repository contains the implementation for my Master's thesis: Inpainting of unseen façade objects using deep learning methods

Official code for paper: Scaling Mesh Generation via Compressive Tokenization [CVPR'25]

[SIGGRAPH 2024] "EASI-Tex: Edge-Aware Mesh Texturing from Single Image", ACM Transactions on Graphics.

Official repo for paper "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling".

[ECCV 2022] SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud

Official code of paper: MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly.