AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

End-to-End Wireframe Parsing

Yichao Zhou, Haozhi Qi, Yi Ma

ICCV 2019 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 248 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 static line sampler (S+, S-) to random dynamic sampler (ablation)L-CNN · ShanghaiTech ablationsAP5: 43.7 -> 47.8Improved
add dynamic sampler candidates D+ and D- (and S+, S-) (ablation)L-CNN · ShanghaiTech ablationsAP5: 47.8 -> 58.9Improved
use dynamic sampler on predicted junctions instead of only static samples from ground truth (ablation)L-CNN · ShanghaiTech ablationsAP5: 38.5 -> 43.7Improved
add hard negative samples S- and D- (ablation)L-CNN · ShanghaiTech ablationsAP5: 57.4 -> 58.9Improved
add hard negative samples S- and D- (ablation)L-CNN · ShanghaiTech ablationsAP10: 61.4 -> 62.9Improved
replace conv+fc head with fc+fc head in line verification network (ablation)L-CNN · ShanghaiTech ablationsAP5: 55.7 -> 58.9Improved
replace conv+fc head with fc+fc head in line verification network (ablation)L-CNN · ShanghaiTech ablationsAP15: 61.7 -> 64.7Improved
train end-to-end wireframe parser (L-CNN) instead of Wireframe parser two-stage heuristicL-CNN · ShanghaiTech testsAP10: 5.1 -> 62.9Improved
L-CNN instead of AFM line detectorL-CNN · ShanghaiTech testAPH: 69.5 -> 83.0Improved
L-CNN instead of AFM line detectorL-CNN · ShanghaiTech testFH: 77.2 -> 81.2Improved
L-CNN instead of AFM when tested on York Urban without finetuningL-CNN · York UrbansAP10: 3.5 -> 26.4Improved

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