AI Paper Atlas

Research map / 3D vision / Face and shape

Efficient 3D Room Shape Recovery From a Single Panorama

Hao Yang, Hui Zhang

CVPR 2016 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 83 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 reconstruction instead of GCSurface label classification · Indoor panoramas, all pixelsclassification error (%): 44.5 -> 26.9Improved
use the proposed reconstruction instead of GCSurface label classification · Indoor panoramas, GCclutter < 0.7classification error (%): 44.4 -> 26.8Improved
use the proposed reconstruction instead of GCSurface label classification · Indoor panoramas, GCclutter < 0.3classification error (%): 48.7 -> 26.7Improved
remove geometric context prior (ablation)Proposed reconstruction · Surface label classification, all pixelsclassification error (%): 26.9 -> 31.8Hurt
remove geometric context prior (ablation)Proposed reconstruction · Surface label classification, GCclutter < 0.7classification error (%): 26.8 -> 31.7Hurt
remove geometric context prior (ablation)Proposed reconstruction · Surface label classification, GCclutter < 0.3classification error (%): 26.7 -> 28.6Hurt
use the proposed reconstruction instead of aligned cuboidsRoom depth estimation · Indoor panoramascosine distance (×10⁻²): 5.23 -> 4.27Improved
use the proposed reconstruction instead of aligned cuboidsRoom depth estimation · Indoor panoramasL2 distance (×10⁻²): 28.48 -> 27.02Improved
assume no occlusions (ablation)Proposed reconstruction · Room depth estimationcosine distance (×10⁻²): 4.27 -> 4.53Hurt
assume no occlusions (ablation)Proposed reconstruction · Room depth estimationL2 distance (×10⁻²): 27.02 -> 27.85Hurt
use ground-truth occlusions (ablation)Proposed reconstruction · Room depth estimationcosine distance (×10⁻²): 4.27 -> 4.23No clear effect
use ground-truth occlusions (ablation)Proposed reconstruction · Room depth estimationL2 distance (×10⁻²): 27.02 -> 27.09No 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