AI Paper Atlas

Research map / 3D vision / Depth and stereo

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Cheng Sun, Chi-Wei Hsiao, Ning-Hsu Wang, Min Sun, Hwann-Tzong Chen

CVPR 2021 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 9 citations (OpenAlex)

Check 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 the proposed divide-and-conquer method rather than PlaneAEIndoor panorama planar reconstruction · Matterport3D testPer-pixel recall: 0.498 -> 0.544Improved
Use the proposed divide-and-conquer method rather than PlaneAEIndoor panorama planar reconstruction · Stanford2D3D validationPer-plane recall: 0.341 -> 0.430Improved
Use the proposed divide-and-conquer method rather than PlaneAEIndoor panorama planar reconstruction · Structured3D testPer-pixel recall: 0.728 -> 0.794Improved
Add yaw-invariant parameterization (ablation)V-plane orientation estimation · Stanford2D3D validationV-plane orientation error (deg): 7.29 -> 5.18Improved
Add CoordConv to yaw-invariant parameterization (ablation)V-plane orientation estimation · Stanford2D3D validationV-plane orientation error (deg): 5.18 -> 5.21No clear effect
Add yaw-invariant parameterization (ablation)PlaneRCNN · Stanford2D3D validationPer-pixel recall: 0.452 -> 0.481Improved
Add yaw-invariant parameterization (ablation)PlaneAE · Stanford2D3D validationPer-plane recall: 0.341 -> 0.368Improved
Add orientation grouping (ablation)Proposed system without yaw-invariant representation · Stanford2D3D validationPer-pixel recall: 0.545 -> 0.627Improved
Add yaw-invariant representation (ablation)Proposed system without orientation grouping · Stanford2D3D validationPer-plane recall: 0.417 -> 0.430Improved
Replace two binary planar classifiers with 3-way softmax classification (ablation)H&V-planar segmentation · PanoH&VPerformanceNo clear effect

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