AI Paper Atlas

Research map / 3D vision / 3D generation

PanelNet: Understanding 360 Indoor Environment via Panel Representation

Haozheng Yu, Lu He, Bing Jian, Weiwei Feng, Shan Liu

CVPR 2023 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 20 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 PanelNet instead of the strongest listed baselineindoor panorama depth estimation · Stanford2D3DMRE: 0.1014 -> 0.0829Improved
Use PanelNet instead of the strongest listed baselineindoor panorama depth estimation · Matterport3DMRE: 0.1387 -> 0.1150Improved
Use PanelNet for RGB semantic segmentationStanford2D3D semantic segmentation · Stanford2D3DmIoU: +3.0Improved
Use PanelNet for layout estimationPanoContext layout estimation · PanoContext3DIoU (%): 85.16 -> 84.52Hurt
Add global panel geometry embedding (ablation)ResNet-34 depth baseline · Stanford2D3DMRE: 0.1033 -> 0.1029Improved
Add global and local panel geometry embedding (ablation)ResNet-34 depth baseline · Stanford2D3DMRE: 0.1033 -> 0.1000Improved
Add Panel Blocks (ablation)ResNet-34 depth baseline · Stanford2D3DMRE: 0.1033 -> 0.0904Improved
Add Window Blocks alongside Panel Blocks (ablation)ResNet-34 depth baseline · Stanford2D3DMRE: 0.0904 -> 0.0854Improved
Add local and global geometry embedding and Panel Blocks (ablation)ResNet-34 depth baseline · Stanford2D3DMRE: 0.1033 -> 0.0851Improved
Add Window Blocks to the geometry-embedding and Panel-Block model (ablation)ResNet-34 depth baseline · Stanford2D3DMRE: 0.0851 -> 0.0829Improved
Remove Local2Global Transformer (ablation)PanelNet · Stanford2D3DMRE: 0.0829 -> 0.1000Hurt
Replace tangent-image input with panel representation (ablation)CNN-based panorama depth estimation · Stanford2D3DMRE: 0.1132 -> 0.1000Improved

Earlier methods this paper compares with

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