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

GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?

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

Code for the SIGGRAPH 2022 paper "DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds."

Codes for automatic point-cloud-to-BIM conversion

Linked Dynamic Graph CNN: Learning through Point Cloud by Linking Hierarchical Features

Code for "Rethinking the compositionality of point clouds through regularization in the hyperbolic space" (NeurIPS 2022)

[ICRA 2023] Official implementation of the paper "ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding"

3D modeling of urban forests based on LiDAR point clouds

Official code of paper "Efficient Joint Gradient Based Attack Against SOR Defense for 3D Point Cloud Classification" (MM'2020)

[MMSP 2023, PCS 2024]

PyTorch implementation of SimpleView from "Revisiting Point Cloud Classification with a Simple and Effective Baseline", Goyal et al. (2020)

Paper on 3D Point Cloud Processing

SE-PseudoGrid for the AutoCon journal paper.

Tutorials for pointcloud processing in Python (transformations, spatial indexing, subsampling, cleaning, normals & curvatures, descriptors, segmentation, primitive fitting, registration & machine learning)

Directional PointNet: 3D Environmental Classification for Wearable Robots

Implementation of point transformer for point cloud classification and segmentation

This repository contains my paper reviews, solutions and code submissions for projects completed as part of CMSC848F during Fall 2023. Each project is organized in its own folder, with accompanying documentation and any necessary resources.

Python SDK for running cloud-based 3D data workflows on the DataFre8 platform.

This repository refers to my master's thesis in the Data Science at Sapienza University. The objective is to build a model in order to perform the task of 3D fragment matching. Given two 3D scans of fragments, the model must predict whether they are adjacent or not.