AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Learning Superpoint Graph Cut for 3D Instance Segmentation

Le Hui, Linghua Tang, Yaqi Shen, Jin Xie, Jian Yang

NeurIPS 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 2 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 coordinate-space edge embedding (ablation)GraphCut · ScanNet v2 valAP: 50.1 -> 50.9Improved
add feature-space edge embedding (ablation)GraphCut · ScanNet v2 valAP: 50.1 -> 51.5Improved
use both coordinate and feature edge embeddings (ablation)GraphCut · ScanNet v2 valAP: 50.1 -> 52.2Improved
add area constraint loss (ablation)GraphCut · ScanNet v2 valAP: 47.8 -> 51.7Improved
add feature loss constraint (ablation)GraphCut · ScanNet v2 valAP: 47.8 -> 51.2Improved
use both area and feature losses (ablation)GraphCut · ScanNet v2 valAP: 47.8 -> 52.2Improved
replace MLP+max-pool with bilateral graph attention (ablation)GraphCut · ScanNet v2 valAP: 49.9 -> 52.2Improved
k-NN size k=2 vs k=4 (ablation)GraphCut · ScanNet v2 valAP: 52.2 -> 52.0Hurt
k-NN size k=8 vs k=4 (ablation)GraphCut · ScanNet v2 valAP: 52.2 -> 51.4Hurt
k-NN size k=16 vs k=4 (ablation)GraphCut · ScanNet v2 valAP: 52.2 -> 50.8Hurt
GraphCut vs second-best method SSTNetGraphCut · ScanNet v2 hidden testAP: 50.6 -> 55.2Improved
GraphCut vs SoftGroupGraphCut · S3DIS Area 5AP: 51.6 -> 54.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

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