LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning

TL;DR

LIDARLearn is a comprehensive, unified PyTorch library that standardizes 3D point cloud deep learning models, training, and evaluation, facilitating fair comparisons and extensive experimentation.

Contribution

It introduces a unified framework integrating diverse models, training protocols, and evaluation tools for 3D point cloud analysis in a single extensible library.

Findings

Supports over 55 model configurations across multiple tasks.

Includes automated statistical testing and visualization tools.

Provides a rigorous, end-to-end testing suite for all configurations.

Abstract

Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring. Although numerous deep learning methods have been proposed for point cloud understanding, including supervised backbones, self-supervised pre-training (SSL), and parameter-efficient fine-tuning (PEFT), their implementations are scattered across incompatible codebases with differing data pipelines, evaluation protocols, and configuration formats, making fair comparisons difficult. We introduce \lib{}, a unified, extensible PyTorch library that integrates over 55 model configurations covering 29 supervised architectures, seven SSL pre-training methods, and five PEFT strategies, all within a single registry-based framework supporting classification, semantic segmentation, part segmentation, and few-shot learning. \lib{} provides standardised training runners, cross-validation with stratified $K$-fold splitting, automated LaTeX/CSV table generation, built-in Friedman/Nemenyi statistical testing with critical-difference diagrams for rigorous multi-model comparison, and a comprehensive test suite with 2\,200+ automated tests validating every configuration end-to-end. The code is available at https://github.com/said-ohamouddou/LIDARLearn under the MIT licence.