AI Paper Atlas

Research map / 3D vision / 3D generation

Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

Rui Huang, Songyou Peng, Ayca Takmaz, Federico Tombari, Marc Pollefeys, Shiji Song, Gao Huang, Francis Engelmann

ECCV 2024 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 46 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 self-supervised fine-tuning on full point clouds with high-confidence predicted masks (ablation)Segment3D · ScanNet++ valAP: 7.4 -> 12.0Improved
train on SAM-generated masks instead of manual 3D labelsMask3D architecture · ScanNet++ val, small masksAP50: 4.5 -> 15.9Improved
train on SAM-generated masks instead of manual 3D labelsMask3D architecture · ScanNet++ val, large masksAP50: 30.6 -> 30.4No clear effect
use a native 3D model on SAM labels instead of SAM3D mergingSegment3D · ScanNet++ valAP: 3.9 -> 12.0Improved
increase number of queries from 100 to 400 (ablation)Segment3D · ScanNet++ valAP: 8.5 -> 12.0Improved
add 34k ScanNet++ frames to pre-training data (ablation)Segment3D · ScanNet++ valAP50: 22.7 -> 24.7Improved
replace Mask3D with Segment3D as mask generator in OpenMask3DOpenMask3D · ScanNet++ open-setAP50: 15.0 -> 17.7Improved
replace Mask3D with Segment3D, transfer indoor-trained models to outdoor scenesSegment3D · Paris-Lille-3DAP50: 1.5 -> 4.0Improved
vary number of queries for Mask3D (ablation)Mask3D · ScanNet++ valAPNo clear effect

Later papers that compared with this method

1 later accepted paper reports Segment3D 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