AI Paper Atlas

Research map / 3D vision / Face and shape

Holistic Geometric Feature Learning for Structured Reconstruction

Ziqiong Lu, Linxi Huan, Qiyuan Ma, Xianwei Zheng

ICCV 2023 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 5 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 frequency-domain feature learning (F-Learn) after first conv of HEATHEAT (ResNet50) · SpaceNet roof graphsregion F1 (%): 70.0 -> 73.4Improved
replace frequency-domain module with space-domain BConv/cascade/parallel modules (ablation)HEAT · SpaceNet roof graphsedge F1 (%): F-Learn 79.1 vs best space-domain 77.1Improved
space-domain conv modules added in place of F-Learn (ablation)HEAT · SpaceNet roof graphscorner F1 (%): 87.1 -> 88.1 (Cas.), 87.4 (BConv), 87.7 (Par.) vs F-Learn 88.6Mixed
apply F-Learn at deeper, lower-resolution layer (L2, 32x32) instead of first conv (ablation)HEAT · SpaceNet roof graphsregion F1 (%): 73.4 -> 69.0 (HEAT baseline 70.0)Hurt
apply F-Learn at L1 (64x64) instead of L0 (ablation)HEAT · SpaceNet roof graphsregion F1 (%): 73.4 -> 70.9Hurt
add F-Learn to HEAT with ResNet18 backbone (ablation)HEAT ResNet18 · SpaceNet roof graphsregion F1 (%): 68.2 -> 69.3Improved
add F-Learn to HEAT with ResNet34 backbone (ablation)HEAT ResNet34 · SpaceNet roof graphsregion F1 (%): 68.0 -> 69.6Improved
add F-Learn with ground-truth corners (topology inference only) (ablation)HEAT · SpaceNet roof graphs (GT corners)edge F1 (%): 88.5 -> 91.1Improved
add space-domain BConv instead of F-Learn with GT corners (ablation)HEAT · SpaceNet roof graphs (GT corners)region F1 (%): 81.2 -> 79.6Hurt
add F-Learn moduleHEAT · SpaceNet roof graphsparameters and time per image: 68.747M -> 68.847M params; 0.10s -> 0.11sNo 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