AI Paper Atlas

Research map / 3D vision / Face and shape

Generative Multiplane Images: Making a 2D GAN 3D-Aware

Xiaoming Zhao, Fangchang Ma, David Güera, Zhile Ren, Alexander G. Schwing, Alex Colburn

ECCV 2022 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 55 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 discriminator pose conditioning to the MPI branch (ablation)GMPI (naive MPI, 32 planes) · FFHQ 512Depth error: 2.190 -> 0.501Improved
add discriminator pose conditioning to the MPI branch (ablation)GMPI (naive MPI, 32 planes) · FFHQ 512Pose error: 0.062 -> 0.006Improved
add plane-specific depth-conditioned feature without pose conditioning (ablation)GMPI · FFHQ 512Depth error: 2.190 -> 2.140No clear effect
add plane-specific feature on top of discriminator pose conditioning (ablation)GMPI with DPC · FFHQ 512Depth error: 0.501 -> 0.462Improved
add discriminator pose conditioning (3D-awareness) at cost of 2D quality (ablation)GMPI with plane feature · FFHQ 512FID: 4.35 -> 7.19Hurt
add shading-guided training (ablation)GMPI with DPC and plane feature · FFHQ 512Depth error: 0.462 -> 0.457No clear effect
increase planes at inference from 32 to 96 (ablation)GMPI · FFHQ 512FID: 7.40 -> 8.29Hurt
increase training planes from 4 to 32 (ablation)GMPI · FFHQ 512Depth error: 0.992 -> 0.457Improved
increase training planes from 4 to 32 (ablation)GMPI · FFHQ 512FID: 16.4 -> 7.40Improved
add camera pose noise during training (0 to 4 sigma) (ablation)GMPI · FFHQ 512Depth error: 0.46 -> 1.68Hurt
lower truncation psi from 1.0 to 0.5 at inference (ablation)GMPI · FFHQ 256Depth error: 0.533 -> 0.445Improved
predict alpha maps directly instead of from a depth map (D2A) (ablation)GMPI · FFHQ 256Depth error: 0.63 -> 0.53Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 5 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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