# QingyongHu/SoTA-Point-Cloud

🔥[IEEE TPAMI 2020] Deep Learning for 3D Point Clouds: A Survey

Repository: https://github.com/QingyongHu/SoTA-Point-Cloud
Canonical: https://ross.abutalabs.com/products/sota-point-cloud
License Family: other
Topics: pointclouds, 3d-deep-learning, 3d-classification, 3d-detection, 3d-tracking, 3d-segmentation, semantic-segmentation, instance-segmentation
Last push: 2021-06-08T07:29:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2443, "days_push": 1912, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1634, forks 187 (observed 2026-08-28T04:05:14.361847+00:00)

## What it is
The official repository accompanying the IEEE TPAMI 2020 survey 'Deep Learning for 3D Point Clouds: A Survey'. It curates papers, datasets, and benchmark results for 3D point cloud tasks such as shape classification, object detection, and segmentation.

## Use cases
- find state-of-the-art methods for 3d point cloud classification
- look up benchmark results on ModelNet40 and ScanObjectNN
- find datasets for 3d object detection research
- get an overview of deep learning approaches for point cloud segmentation
- start researching 3d deep learning for a literature review
- track recent papers on 3d point cloud tracking

## When to choose
- you need a curated survey of point cloud deep learning methods with links to papers and datasets
- you want benchmark comparisons across public 3d datasets
- you are starting research in 3d vision and need a taxonomy of approaches

## When to avoid
- you need runnable code or a library rather than a paper list
- you need coverage of methods published after the survey's last update
- you want a maintained tool with a software license

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, computer-vision, documentation
- domain: computer-vision, deep-learning, machine-learning, tutorials
- platform: cross-platform
- tags: point-clouds, 3d-deep-learning, survey, awesome-list, 3d-classification, 3d-object-detection, 3d-segmentation, paper-list

## Member repositories
- QingyongHu/SoTA-Point-Cloud (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:14.361847+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:47:03.128736+00:00, confidence not recorded.
  - readme: https://github.com/QingyongHu/SoTA-Point-Cloud (fetched 2026-08-28T04:05:14.361847+00:00, sha e1f0604e8902)
- Data as of 2026-08-30T08:39:29.467469+00:00.