AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DeepCAD: A Deep Generative Network for Computer-Aided Design Models

Rundi Wu, Chang Xiao, Changxi Zheng

ICCV 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 262 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 random command-sequence augmentation (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)median chamfer distance: 0.787 -> 0.752Improved
add random command-sequence augmentation (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)invalid ratio: 3.30 -> 2.72Improved
quantize continuous parameters instead of regressing them (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)median chamfer distance: 2.142 -> 0.787Improved
quantize continuous parameters instead of regressing them (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)invalid ratio: 4.32 -> 3.30Improved
use absolute curve positions instead of relative positions (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)median chamfer distance: 0.863 -> 0.787Improved
use absolute curve positions instead of relative positions (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)ACC_param: 97.66 -> 97.47Hurt
translate sketch origin to loop start instead of adding loop start to extrusion command (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)median chamfer distance: 0.792 -> 0.787No clear effect
specify arcs by sweep angle and flag instead of middle point (ablation)DeepCAD autoencoder · DeepCAD test set (autoencoding)median chamfer distance: 0.790 -> 0.787No clear effect
DeepCAD generation compared with l-GANDeepCAD · DeepCAD shape generationJSD: 5.02 -> 3.76Improved
DeepCAD generation compared with l-GANDeepCAD · DeepCAD shape generationMMD: 1.27 -> 1.45Hurt
add uniform noise to input point cloudsDeepCAD point cloud to CAD · Point cloud to CAD reconstructioninvalid ratio: 12.08 -> 13.82Hurt

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