Computer vision & multimodal· 2016
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
On the reading lists
- #241 in the Top 500 (2026 edition)
- #45 in Computer vision & multimodal (2026 edition)
Why it matters
Established permutation-invariant deep learning directly on unordered 3D point sets.
Condensed from the expert lists' notes.
The record
- First released
- 2016 (from arXiv 1612.00593)
- Published
- 2017
- Citations
- 18,771 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Also relevant to
- Graph learning
- Score
- 0.489 · computed rank 241 · consensus 0.57, must-read 0.5, citations percentile 0.765 (2010s · vision), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.