AI Paper Atlas

Research map / 3D vision / Face and shape

Multimodal Shape Completion via Conditional Generative Adversarial Networks

Rundi Wu, Xuelin Chen, Yixin Zhuang, Baoquan Chen

ECCV 2020 · 3D vision › Face and shape · approach: 3D shape generative modeling · 86 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 explicit mode encoder (shape VAE encoder) instead of implicit point-cloud mode encoder (ablation)Ours-im-pc2z · PartNetTMD x10^2 (diversity): 0.69 -> 3.12Improved
add explicit mode encoder instead of implicit point-cloud mode encoder (ablation)Ours-im-pc2z · PartNetMMD x10^3 (quality): 2.00 -> 1.65Improved
add explicit mode encoder instead of implicit point-cloud mode encoder (ablation)Ours-im-pc2z · PartNet-ScanTMD x10^2 (diversity): 1.42 -> 3.65Improved
add explicit mode encoder instead of implicit point-cloud mode encoder (ablation)Ours-im-pc2z · 3D-EPNTMD x10^2 (diversity): 1.33 -> 3.03Improved
add explicit mode encoder instead of implicit latent-code mode encoder (ablation)Ours-im-l2z · PartNetUHD x10^2 (fidelity, lower better): 7.33 -> 6.06Improved
add explicit mode encoder instead of implicit latent-code mode encoder (ablation)Ours-im-l2z · PartNetMMD x10^3 (quality): 1.93 -> 1.65Improved
add explicit mode encoder instead of implicit latent-code mode encoder (ablation)Ours-im-l2z · PartNetTMD x10^2 (diversity): 3.34 -> 3.12Hurt
add explicit mode encoder instead of implicit latent-code mode encoder (ablation)Ours-im-l2z · 3D-EPNMMD x10^3 (quality): 1.80 -> 1.67Improved
use learned conditional GAN instead of nearest-neighbor retrieval in latent spaceKNN-latent · PartNetMMD x10^3 (quality): 1.47 -> 1.65Hurt
increase weight beta of latent regression loss (ablation)Ours · PartNetTMD (diversity) and UHD (fidelity)Mixed
increase weight of reconstruction loss (ablation)Ours · PartNetdiversity of completionsHurt
increase number of missing parts in inputOurs · PartNetTMD (diversity)Improved

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