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

2026-04-12

AI Summary

This work addresses the challenge of fair comparison among existing deep learning methods for 3D point clouds, which is hindered by fragmented implementations, incompatible codebases, and inconsistent evaluation protocols. To this end, the authors propose a unified and extensible PyTorch library that, for the first time, integrates 29 supervised models, 7 self-supervised pretraining approaches, and 5 parameter-efficient fine-tuning strategies within a single registration framework, supporting tasks including classification, semantic segmentation, part segmentation, and few-shot learning. The library offers standardized training pipelines, hierarchical k-fold cross-validation, automated result analysis with Friedman and Nemenyi statistical significance tests, and LaTeX/CSV table generation. Validated through over 2,200 end-to-end experiments across more than 55 model configurations, it substantially enhances reproducibility, comparability, and research efficiency. The code is publicly released under the MIT license.

Technology Category

Computer Vision: 3D Computer VisionMachine Learning: Deep Generative Models & AutoencodersReasoning under Uncertainty: Relational Probabilistic Models

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSemantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semanticsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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.

Problem

• 3D point cloud
• deep learning
• self-supervised learning
• model comparison
• codebase fragmentation

Innovation

• unified deep learning library
• 3D point cloud analysis
• self-supervised pre-training
• parameter-efficient fine-tuning
• rigorous model comparison