AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Scalable SoftGroup for 3D Instance Segmentation on Point Clouds

Thang Vu, Kookhoi Kim, Thanh Nguyen, Tung M. Luu, Junyeong Kim, Chang D. Yoo

TPAMI 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 49 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 soft grouping (ablation)hard-grouping baseline · ScanNet v2 valAP50: 61.1 -> 63.8Improved
add top-down refinement (ablation)hard-grouping baseline · ScanNet v2 valAP50: 61.1 -> 65.4Improved
add top-down refinement to soft grouping (ablation)SoftGroup · ScanNet v2 valAP50: 63.8 -> 67.6Improved
use soft grouping score threshold 0.01 instead of hard prediction (ablation)SoftGroup · ScanNet v2 valAP50: 65.4 -> 58.5Hurt
set soft grouping threshold 0.2 instead of none (ablation)SoftGroup · ScanNet v2 valAP: 44.3 -> 46.0Improved
add mask branch to class-only top-down refinement (ablation)SoftGroup · ScanNet v2 valAP: 41.1 -> 45.7Improved
add mask scoring branch (ablation)SoftGroup · ScanNet v2 valAP50: 68.4 -> 67.6Mixed
replace naive scaling with class-aware pyramid scaling (CAPS) (ablation)SoftGroup++ · S3DIS Area 5AP: 47.0 -> 50.9Improved
add octree k-NN (ablation)SoftGroup++ baseline · S3DIS largest scenetotal runtime (s): 30.32 -> 9.85Improved
add late devoxelization (ablation)SoftGroup++ baseline · S3DIS largest scenetotal runtime (s): 30.32 -> 2.05Improved
add octree k-NN to CAPS plus late devoxelization (ablation)SoftGroup++ · S3DIS largest scenek-NN runtime (s): 0.50 -> 0.44Improved
add octree k-NN (ablation)SoftGroup++ · STPLS3D uncroppedk-NN runtime (s): 1.48 -> 0.93Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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