AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Procedural Reconstruction for Residential Buildings

Huayi Zeng, Jiaye Wu, Yasutaka Furukawa

ECCV 2018 · 3D vision › Face and shape · approach: 3D shape generative modeling · 34 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 dormer augmentation to training data (ablation)NPR dormer detection · Dormer detection (3 px)precision and recall: (8% and 17%) to (77% and 84%)Improved
add synthetic data (x40) to real training data (ablation)NPR foundation classification · Foundation classificationaccuracy: 82.2 -> 89.2Improved
add synthetic data (x10) to real training data (ablation)NPR foundation classification · Foundation classificationaccuracy: 82.2 -> 85.3Improved
add more synthetic data (x50 vs x40) (ablation)NPR foundation classification · Foundation classificationaccuracy: 89.2 -> 88.7No clear effect
add synthetic data to real training data (ablation)NPR II-foundation regression · II-foundation regressionIoU: 0.796 -> 0.815No clear effect
train on synthetic data only (x10 to x50) (ablation)NPR foundation classification · Foundation classificationaccuracy: 89.2 -> 42.0Hurt
train regression on synthetic data only instead of real plus synthetic (ablation)NPR II-foundation regression · II-foundation regressionIoU: 0.815 -> 0.803Hurt
replace Poisson+QSlim reconstruction with NPRresidential LiDAR reconstruction · Residential LiDAR (250 houses)mean absolute distance: 1.47 -> 0.81Improved
replace piecewise planar reconstruction with NPRresidential LiDAR reconstruction · Residential LiDAR (250 houses)mean absolute distance: 0.95 -> 0.81Improved
replace Kentucky bottom-up decomposition with NPRresidential LiDAR reconstruction · Residential LiDAR (250 houses)mean absolute distance: 2.13 -> 0.81Improved
replace USC with NPRresidential LiDAR reconstruction · Residential LiDAR (250 houses)number of triangles: 169.0 -> 45.5Improved
replace piecewise planar with NPR on U-foundation housesresidential LiDAR reconstruction · Residential LiDAR (U-foundation houses)mean absolute distance: 0.80 -> 0.84Hurt

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