AI Paper Atlas

Research map / 3D vision / 3D generation

Complete 3D Scene Parsing from an RGBD Image

Chuhang Zou, Ruiqi Guo, Zhizhong Li, Derek Hoiem

IJCV 2018 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 32 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 support height feature to region classification (ablation)Region classification CNN · 81-class region classification (GT regions)avg per class accuracy (%): 43.7 -> 44.7Improved
Add support height feature, regions with occlusion ratio above 0.5 (ablation)Region classification CNN · Region classification, occlusion > 0.5accuracy (%): 35.7 -> 38.5Improved
Add support height feature, regions with occlusion ratio below 0.5 (ablation)Region classification CNN · Region classification, occlusion < 0.5accuracy (%): 44.2 -> 45.8Improved
Add support height to the scene parsing pipeline (ablation)Full pipeline · NYUd v2 84-class semantic segmentationavg class accuracy: 10.51 -> 10.77Improved
Add support height to the scene parsing pipeline (ablation)Full pipeline · NYUd v2 84-class instance segmentationmean coverage unweighted: 34.34 -> 33.92Hurt
Use ground truth support height instead of predicted (ablation)Full pipeline · NYUd v2 84-class semantic segmentationavg class accuracy: 10.77 -> 11.28Improved
Use ground truth regions instead of automatic region proposals (ablation)Full pipeline · NYUd v2 84-class semantic segmentationavg class accuracy: 10.77 -> 16.63Improved
Use learned retrieval of similar shapes instead of Guo et al.Shape retrieval · NYUd v2 shape retrievalavg class accuracy top 1 (%): 11.97 -> 41.56Improved
Model layout in 3D with full pipeline instead of Guo et al.Layout estimation · NYUd v2 layout depthoverall depth error: 0.166 -> 0.150Improved
Compare against Deep Sliding Shapes on 3D amodal detectionFull pipeline · NYUd v2 3D amodal detectionchair mAP (%): 61.1 -> 3.1Hurt
Compare against SSCNet on scene completionFull pipeline · NYUd v2 scene completionIoU: 55.1 -> 49.4Hurt

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