AI Paper Atlas

Research map / Point clouds / Segmentation and detection

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

Zihui Zhang, Bo Yang, Bing Wang, Bo Li

CVPR 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 70 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
remove superpoint construction and progressive growing (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 20.3±0.4Hurt
replace semantic primitive clustering with direct 12-class grouping (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 25.4±1.0Hurt
remove PFH geometry features from semantic clustering (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 38.9±0.9Hurt
use 25cm rather than 50cm initial voxels (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 41.3±1.8Hurt
use 75cm rather than 50cm initial voxels (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 43.2±0.7Hurt
set M1 to 160 (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 43.3±1.3Hurt
set M1 to 120 (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 41.3±3.2Hurt
set M1 to 40 (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 43.1±2.0Hurt
set final superpoint count MT to 60 (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 42.4±1.1Hurt
set final superpoint count MT to 40 (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 43.0±0.8Hurt
set final superpoint count MT to 12 (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 38.9±3.0Hurt
reduce superpoint count by 1 every 40 epochs (ablation)GrowSP · S3DIS Area-5mIoU: 44.5±1.1 -> 42.2±2.4Hurt

Later papers that compared with this method

4 later accepted papers report GrowSP as a baseline in their results tables; 4 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