AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Instance Segmentation in 3D Scenes Using Semantic Superpoint Tree Networks

Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia

ICCV 2021 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 130 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
build SST from instance centers rather than superpoint features (ablation)SSTNet · ScanNet v2 valmAP: 40.1 -> 47.3Improved
build SST from semantic scores rather than superpoint features (ablation)SSTNet · ScanNet v2 valmAP: 40.1 -> 43.5Improved
use semantic score plus instance center instead of all three features (ablation)SSTNet · ScanNet v2 valmAP: 48.9 -> 49.4Improved
add superpoint feature to score and center for SST construction (ablation)SSTNet · ScanNet v2 valmAP: 49.4 -> 48.9Hurt
learn node-splitting classifier instead of thresholding distance (ablation)SST traversal · ScanNet v2 valmAP: 46.3 -> 49.4Improved
learn node-splitting classifier instead of thresholding distance (ablation)SST traversal · ScanNet v2 valAP@25: 74.7 -> 74.0Hurt
use semantic superpoint tree instead of kNN superpoint graph (ablation)SSTNet · ScanNet v2 valmAP: 44.4 -> 49.4Improved
add CliqueNet refinement (ablation)SSTNet · ScanNet v2 valmAP: 49.4 -> 50.0Improved
add CliqueNet refinement (ablation)SSTNet · ScanNet v2 valAP@50: 64.3 -> 64.7Improved
add CliqueNet refinement (ablation)SSTNet · ScanNet v2 valAP@25: 74.0 -> 73.9No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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