AI Paper Atlas

Research map / 3D vision / Depth and stereo

Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image

Wei Zeng, Sezer Karaoglu, Theo Gevers

ECCV 2020 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 48 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 predicted depth as input to layout depth network (ablation)layout depth network · Stanford 2D-3D layout3D IoU (%): 77.28 -> 82.65Improved
add predicted semantics as input to layout depth network (ablation)layout depth network · Stanford 2D-3D layout3D IoU (%): 77.28 -> 78.57Improved
add both depth and semantics as input (ablation)layout depth network · Stanford 2D-3D layout3D IoU (%): 77.28 -> 85.81Improved
add virtual normal loss (ablation)layout depth network · Stanford 2D-3D layout3D IoU (%): 84.22 -> 85.81Improved
add virtual normal loss (ablation)layout depth network · Stanford 2D-3D layoutcorner error (%): 0.75 -> 0.67Improved
predict layout depth map instead of edge and corner maps (ablation)layout network · Stanford 2D-3D layout3D IoU (%): 82.03 -> 85.81Improved
predict layout depth map instead of edge/corner maps converted from layout depth (ablation)layout network · Stanford 2D-3D layout3D IoU (%): 83.67 -> 85.81Improved
add layout-depth refinement (direct refinement) (ablation)depth network · Stanford 2D-3D depthAbs Rel: 0.105 -> 0.089Improved
use semantic-guided fusion instead of direct refinement (ablation)depth network · Stanford 2D-3D depthAbs Rel: 0.089 -> 0.086Improved
add final refinement after semantic-guided fusion (ablation)depth network · Stanford 2D-3D depthAbs Rel: 0.086 -> 0.068Improved
train coarse depth module jointly (ablation)coarse depth · Stanford 2D-3D depthAbs Rel: 0.112 -> 0.105Improved
train depth refinement jointly (ablation)depth refinement · Stanford 2D-3D depthAbs Rel: 0.084 -> 0.068Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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