Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)

[ECCV'24] OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

Official code release for ConceptGraphs

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

[T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

[ISPRS 2021] Vectorized Indoor Surface Reconstruction from 3D Point Cloud with Multistep 2D Optimization

简单的立体视觉

简单的SLAM视觉里程计

简单的回环检测

Joint Bilateral Upsampling

对论文《Multi-Scale Geometric Consistency Guided Multi-View Stereo》的复现

ucas疫情防控每日填报助手

calibrate a Livox LiDAR and a camera

convert LiDAR point cloud to rosbag

Read Velodyne LiDAR points form .pcap file

C++ version of the BATA(Bilinear Angle-based Translation Averaging) algorithm.

An implementation of paper "Automatic Online Calibration of Cameras and Lasers"

A tool for annotating textured urban meshes

🍀 Official pytorch implementation of "ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation. Wu et al. ICCV 2021."

🍀 Official pytorch implementation of "ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation. Wu et al. ICCV 2021."

A framework for annotating 3D meshes using the predictions of a 2D semantic segmentation model.

An efficient 3D semantic segmentation framework for Urban-scale point clouds like SensatUrban, Campus3D, etc.

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).