AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PUPS: Point Cloud Unified Panoptic Segmentation

Shihao Su, Jianyun Xu, Huanyu Wang, Zhenwei Miao, Xin Zhan, Dayang Hao, Xi Li

AAAI 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 24 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add classifier refinement (ablation)PUPS M1 · SemanticKITTI validationPQ: 44.5 -> 50.9Improved
Add context-aware CutMix (ablation)PUPS M1 · SemanticKITTI validationPQ: 44.5 -> 55.9Improved
Use classifier refinement and context-aware CutMix together (ablation)PUPS · SemanticKITTI validationPQ: 55.9 -> 64.4Improved
Use 3 rather than 1 refinement stage (ablation)PUPS · SemanticKITTI validationPQ: 62.1 -> 64.4Improved
Increase refinement stages from 3 to 4 (ablation)PUPS · SemanticKITTI validationPQ: 64.4 -> 63.2Hurt
Increase refinement stages from 3 to 5 (ablation)PUPS · SemanticKITTI validationPQ: 64.4 -> 63.0Hurt
Use 100 rather than 50 classifiers (ablation)PUPS · SemanticKITTI validationPQ: 63.3 -> 64.4Improved
Increase the classifier count from 100 to 150 (ablation)PUPS · SemanticKITTI validationPQ: 64.4 -> 63.7Hurt
Increase the classifier count from 100 to 200 (ablation)PUPS · SemanticKITTI validationPQ: 64.4 -> 63.8Hurt
Replace random CutMix with context-aware CutMix (ablation)PUPS M1 · SemanticKITTI validationPQ: 50.8 -> 55.9Improved
Use PUPS instead of Panoptic-PHNetSemanticKITTI test · SemanticKITTI testPQ: 61.5 -> 62.2Improved
Use PUPS instead of GP-S3NetSemanticKITTI validation · SemanticKITTI validationPQ: 63.3 -> 64.4Improved

Later papers that compared with this method

1 later accepted paper reports PUPS as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy