🔥3D点云目标检测&语义分割(深度学习)-SOTA方法,代码,论文,数据集等

ROS & ROS2 Implementation of Patchwork++

A fast and memory-efficient libarary for sparse transformer with varying token numbers (e.g., 3D point cloud).

3D点云语义分割汇总，所有顶会论文以及一些arxiv上的最新论文

A C++ version for "A Slope-robust Cascaded Ground Segmentation in 3D Point Cloud for Autonomous Vehicles" 2018 ITSC

This is the official repository of the original Point Transformer architecture.

Fast Segmentation of 3D Point Clouds A Paradigm on LiDAR Data for Autonomous Vehicle Applications

Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter (ECCV 2022)

[ICRA 2024] Official Implementation of the paper "Parameter-efficient Prompt Learning for 3D Point Cloud Understanding"

The four major frameworks for 3D point cloud sparse acceleration, which are currently mainstream, are compared. These include MIT-HAN-LAB's torchsparse, NVIDIA's MinkowskiEngine, TuSimple's spconv, and Facebook Research's SparseConvNet.

Deep 3D Semantic Segmentation of common indoor objects on 3D point clouds .ply datas using RandLANet model with RANSAC based planar estimation post-processing techniques for prediction of vectorized floor plan of indoor scenes.

Extended Kalman Filter and Deep Learning to detect vehicles from RGB and LiDAR data (Sensor Fusion and Tracking project of the Udacity Self-Driving Car Engineer Nanodegree Program)

This is the implementation of Recycle Maxpooling Module for Point Cloud Analysis

The official implementation code of Paper "PointCVaR: Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification" in AAAI 2024 (Oral)

A tutorial for learning the knowledge and techniques about 3D point clouds.

[AAAI 2025] 3DPGS: 3D Probabilistic Graph Search for Archaeological Piece Grouping

Paper on 3D Point Cloud Processing

A PyTorch implementation of Point Transformer that can handle the input data in batch mode.

3DAeroRelief is a high-resolution 3D point cloud benchmark dataset designed for semantic segmentation in post-disaster scenarios. It includes 3D data for eight distinct areas, COLMAP configuration files for reconstruction, and Python utility scripts for merging and processing semantic labels and geometry.

3D Scene Reconstruction Based on Stereo Vision.