Awesome point cloud analysis
A curated list of papers, datasets, and code for 3D point cloud analysis research, covering classification, segmentation, detection, and more.
What is Awesome point cloud analysis?
Awesome Point Cloud Analysis is a curated GitHub repository that serves as a comprehensive resource for researchers and developers working with 3D point cloud data. It aggregates academic papers, datasets, and code implementations related to point cloud processing tasks like classification, segmentation, object detection, and registration. The project solves the problem of fragmented information by providing a single, organized reference point for staying current with advancements in 3D vision research.
Researchers, graduate students, and engineers in computer vision, robotics, and autonomous systems who need to quickly access the latest point cloud analysis literature and resources. It's particularly valuable for those entering the field or starting new projects in 3D deep learning.
Unlike scattered paper lists or personal collections, this repository offers a community-vetted, structured, and continuously updated resource with clear indicators for code availability and paper impact. It saves researchers significant time in literature review and provides immediate access to implementations for reproducibility.
Overview
A list of papers and datasets about point cloud analysis (processing)
Use Cases
Best For
- Finding state-of-the-art point cloud deep learning papers for a specific task (e.g., segmentation)
- Locating publicly available code implementations for point cloud research
- Discovering benchmark datasets for training and evaluating 3D models
- Getting started with point cloud analysis and understanding key methodologies
- Tracking research trends in 3D vision from 2017 onward
- Identifying papers relevant to autonomous driving and LiDAR processing
Not Ideal For
- Engineers needing a production-ready SDK with documentation and support for integrating point cloud processing into applications.
- Beginners seeking hands-on tutorials or step-by-step coding examples to learn point cloud analysis from scratch.
- Projects requiring the absolute latest research papers beyond 2019, as the main list is static and redirects to a separate repository for updates.
- Teams looking for comparative benchmarks or performance evaluations of different point cloud methods, as the list only aggregates papers without analysis.
Pros & Cons
Pros
The README chronologically organizes papers from top conferences since 2017 and uses a consistent keyword taxonomy (e.g., cls., seg., det.) for easy filtering by task, saving researchers time in literature review.
Papers are marked with emojis (🔥 for code available with stars >= 100, ⭐ for citations >= 50), providing immediate visibility into implementable and high-impact research based on community metrics.
It comprehensively covers diverse point cloud tasks like classification, segmentation, detection, and autonomous driving, as evidenced by the keyword list spanning from 'dat.' for datasets to 'aut.' for autonomous driving applications.
The project invites contributions via email and points to a newer repository ('awesome-point-cloud-analysis-2020') for recent papers, demonstrating an effort to stay current through open collaboration.
Cons
The core list stops at 2019 papers, requiring users to visit a separate repository for newer research, which fragments the resource and may lead to outdated references if not actively maintained.
It merely aggregates papers with basic metadata (code links, citations) but lacks qualitative reviews, comparative insights, or benchmark results, leaving users to independently assess paper relevance and performance.
While it lists code implementations, the repository provides no tutorials, setup instructions, or integration help, making it challenging for newcomers to deploy or experiment with the cited methods effectively.
Frequently Asked Questions
Related Projects
Awesome machine learningA curated list of awesome Machine Learning frameworks, libraries and software.
Awesome deep learningA curated list of awesome Deep Learning tutorials, projects and communities.
Awesome computer visionA curated list of awesome computer vision resources
Awesome artificial intelligenceA curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.