AI Paper Atlas

Research map / 3D vision / 3D generation

Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation With Cross-Scale Distortion Awareness

Zhijie Shen, Zishuo Zheng, Chunyu Lin, Lang Nie, Kang Liao, Shuai Zheng, Yao Zhao

CVPR 2023 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 15 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
Use DOPNet instead of LGT-NetCuboid rooms trained on PanoContext + whole Stanford 2D-3D · PanoContext + Stanford 2D-3D3DIoU (%): 85.16 -> 85.46Improved
Use DOPNet instead of Dula-Netv2Cuboid rooms trained on Stanford 2D-3D + whole PanoContext · Stanford 2D-3D + PanoContext3DIoU (%): 86.60 -> 85.47Hurt
Use DOPNet instead of LGT-NetDOPNet · MatterportLayout3DIoU (%): 81.11 -> 81.70Improved
Use DOPNet instead of LGT-NetDOPNet · ZInD3DIoU (%): 89.95 -> 90.13Improved
Add cross-scale interaction (ablation)DOPNet feature assembling · MatterportLayout3DIoU (%): 80.71 -> 81.34Improved
Add distortion elimination and feature assembling (ablation)DOPNet feature extraction · MatterportLayout3DIoU (%): 80.10 -> 81.34Improved
Add orthogonal plane disentanglement (ablation)DOPNet · MatterportLayout3DIoU (%): 80.60 -> 81.34Improved
Add soft-flipping fusion (ablation)DOPNet · MatterportLayout3DIoU (%): 80.35 -> 81.34Improved
Add discriminative channel generation (ablation)DOPNet sequence reconstruction · MatterportLayout3DIoU (%): 80.23 -> 81.34Improved
Add self-attention for long-range dependencies (ablation)DOPNet sequence reconstruction · MatterportLayout3DIoU (%): 80.97 -> 81.34Improved
Add cross-attention residuals (ablation)DOPNet sequence reconstruction · MatterportLayout3DIoU (%): 80.45 -> 81.34Improved

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