A list of papers and datasets about point cloud analysis (processing)

3DGS-to-PC: 3D Gaussian Splatting to Dense Point Clouds [3D-VAST: ICCVW 2025]

Papers, code and datasets about deep learning for 3D Object Detection.

Image Signal Processing (ISP) Guide. Learn all about the process of converting an image/video into digital form by performing tasks like noise reduction, filtering, auto exposure, autofocus, HDR correction, and image sharpening with a Specialized type of media processor.

Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020)

Implementations of a rather simple version of the Iterative Closest Point algorithm in various languages.

C++ library and programs for reading and writing ASPRS LAS format with LiDAR data

Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions (RAL 2022)

Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296

[ICCV 2021] Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

An SDK for multi-agent collaborative perception.

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

[CVPR2023] Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration

PVT: Point-Voxel Transformer for 3D Deep Learning

Probabilistic line extraction from 2-D range scan

Introduction to Point Cloud Processing

Point cloud completion tool based on dictionary learning. Takes a PCL point cloud surface and fills in gaps or densifies sparse regions by learning from the various surface features of the cloud. This is done using a variation of the k-SVD dictionary learning algorithm that allows for continuous atoms and dealing with unstructured point cloud data. Written in Qt C++, using Eigen, OpenMP, and OpenGL.

Utilities for point cloud processing. read ply, write ply, search nearest neighbors using octree ...

Official GitHub repo for VecKM. A very efficient and descriptive local geometry encoder / point tokenizer / patch embedder. ICML2024.

Cross-platform library to communicate with LiDAR devices of the Blickfeld GmbH.

This code is designed to extract a representative curve (or a thin center line) from a noisy 3D point cloud, especially when the point cloud has discernible geometric patterns. Given a noisy point cloud that has an inherent structure or shape, the goal is to identify and trace a continuous curve that best captures the essence of that shape.

FLS point cloud registration (ISRR 2022)

[NeurIPS 2024] Official implementation of the paper "Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis"

Point cloud segmentation with Azure Kinect

diffCheck is a CAD-integrated tool for evaluating digital timber fabrication processes.

[AAAI 2023 Distinguished Paper] Two Heads are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation

Efficient Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction

[JAG 2026] The official implementation of the paper "Dense 3D displacement estimation for landslide monitoring via fusion of TLS point clouds and embedded RGB images".

In this project we detect, segment and track the obstacles of an ego car and its custom implementation of KDTree, obstacle detection, segmentation, clustering and tracking algorithm in C++ and compare it to the inbuilt algorithm functions of PCL library on a LiDAR's point cloud data.