AI Paper Atlas

Research map / 3D vision / Face and shape

Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance

Zhixin Shu, Mihir Sahasrabudhe, Riza Alp Guler, Dimitris Samaras, Nikos Paragios, Iasonas Kokkinos

ECCV 2018 · 3D vision › Face and shape · approach: 3D morphable face model regression · 183 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 integral deformation to affine deformation (ablation)DAE · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 14.13 -> 8.50Improved
train the DAE on CelebA instead of MAFLDAE A+I · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 8.50 -> 7.54Improved
train a landmark regressor on deformation fieldsDAE A+I CelebA · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 7.54 -> 5.96Improved
add regularization on estimated deformations (ablation)DAE latent 32 · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 10.24 -> 5.96Improved
use integral deformation instead of residual deformation grid (ablation)DAE latent 32 · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 9.93 -> 5.96Improved
increase latent size from 16 to 96 (ablation)DAE · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 5.71 -> 6.46Mixed
add dense connections and increase latent size (ablation)DAE · MAFL test (landmark error)mean landmark error (% inter-ocular distance): 6.46 -> 5.45Improved
increase Z_T dimension from 0 to moderate (4-32D) (ablation)DAE · MAFL faces (qualitative)texture alignment and appearance fidelityImproved
increase Z_T to 128-D (ablation)DAE · MAFL faces (qualitative)texture alignmentHurt
use affine+integral warping instead of direct convolutional warp field (ablation)DAE · MAFL faces (qualitative)reconstruction and texture qualityImproved

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