AI Paper Atlas

Research map / 3D vision / Face and shape

Learning to Reconstruct 3D Manhattan Wireframes From a Single Image

Yichao Zhou, Haozhi Qi, Yuexiang Zhai, Qi Sun, Zhili Chen, Li-Yi Wei, Yi Ma

ICCV 2019 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 83 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 offset regression for junctions (l2 loss) (ablation)Joint wireframe network · SU3 validation (3D wireframe)APC: 65.4 -> 72.8Improved
add offset regression for junctions (l2 loss) (ablation)Joint wireframe network · SU3 validation (3D wireframe)APT: 57.1 -> 60.1Improved
use l2 instead of l1 loss for offset regression (ablation)Joint wireframe network · SU3 validation (3D wireframe)APC: 69.3 -> 72.8Improved
use l2 instead of l1 loss for offset regression (ablation)Joint wireframe network · SU3 validation (3D wireframe)APT: 55.8 -> 60.1Improved
add line (edge) supervision jointly with junctions (ablation)Joint wireframe network · SU3 validation (3D wireframe)APC: 72.8 -> 74.3Improved
add line (edge) supervision jointly with junctions (ablation)Joint wireframe network · SU3 validation (3D wireframe)APT: 60.1 -> 61.0Improved
add junction supervision jointly with lines (ablation)Joint wireframe network · SU3 validation (3D wireframe)line heatmap IoU: 73.3 -> 74.2Improved
add ordinal loss to depth supervision (ablation)Joint wireframe network · SU3 validation (3D wireframe)SILog: 3.59 -> 4.14Hurt
add joint junction and line training to depth estimation (ablation)Joint wireframe network · SU3 validation (3D wireframe)SILog: 3.59 -> 3.04Improved
train junctions and lines jointly instead of separately (ablation)Wireframe network · Wireframe dataset (2D)AP: 67.8 -> 71.0Improved
use proposed network instead of prior parser with separate training2D wireframe detection · Wireframe dataset (2D)AP: 67.5 -> 67.8Improved
use neural vanishing point regression instead of LSD/J-linkageVanishing point detection · SU3 vanishing point detectionfailure rate: 20.0% -> 2.3%Mixed

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