AI Paper Atlas

Research map / 3D vision / Face and shape

3D Volumetric Modeling with Introspective Neural Networks

Wenlong Huang, Brian Lai, Weijian Xu, Zhuowen Tu

AAAI 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 19 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
train CNN with introspective reclassification-by-synthesis (3DWINN) instead of plain training (ablation)volumetric CNN · ModelNet10 FGSMadversarial error: 27.64% -> 19.05%Improved
3DWINN vs baseline under iterative FGSM 5 steps (ablation)volumetric CNN · ModelNet10adversarial error: 30.50% -> 19.27%Improved
3DWINN vs baseline under iterative FGSM 10 steps (ablation)volumetric CNN · ModelNet10adversarial error: 53.19% -> 43.83%Improved
3DWINN vs baseline clean accuracy (ablation)volumetric CNN · ModelNet10 supervisedaccuracy: 93.1% -> 93.6%Improved
3DWINN FID vs 3D-DescriptorNet3D generative model · ModelNet10 Chair FIDFID: 490 -> 225Improved
single jointly trained 3DWINN instead of per-category models (ablation)3DWINN · ModelNet10 generationInception score: 10.25 -> 7.81Hurt
3DWINN-separate-multi vs 3D-DescriptorNet3D generative model · ModelNet10 generationInception score: 11.77 -> 10.25Hurt
3DWINN vs 3D-DescriptorNet (unsupervised features + SVM)3D generative model · ModelNet10 unsupervised classificationaccuracy: 92.4% -> 91.9%Hurt
3DWINN vs ORION supervised3D classifier · ModelNet10 supervisedaccuracy: 93.8% -> 93.6%Hurt

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