PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders

Eimear O’ Sullivan, Stefanos Zafeiriou
NeurIPS 2020 Workshop on Pre-registration in Machine Learning, PMLR 148:87-99, 2021.

Abstract

3D Morphable Models have long played a key role in the construction of statistical shape models. While earlier models employed Principal Component Analysis, recent work has migrated towards mesh autoencoder models for the construction of lightweight, non-linear shape models that facilitate state-of-the-art reconstruction and the capture of high-fidelity details. Doing so results in a loss of interpretability and regularisation in the model latent space. To address this, we propose PCA retargeting, a method for expressing linear PCA models as mesh autoencoders and thereby retaining the gaussianity of the latent space. To encourage the capture of mesh details outside the expressive range of a PCA model, we introduce “free” latent space parameters. Experiments demonstrate the successful retargeting of the PCA models as mesh autoencoders. The introduction of “free” latent parameters have a greater impact when smaller latent vector sizes are used, but do not lead to any gains in reconstruction fidelity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v148-o-sullivan21a, title = {PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders}, author = {O' Sullivan, Eimear and Zafeiriou, Stefanos}, booktitle = {NeurIPS 2020 Workshop on Pre-registration in Machine Learning}, pages = {87--99}, year = {2021}, editor = {Bertinetto, Luca and Henriques, João F. and Albanie, Samuel and Paganini, Michela and Varol, Gül}, volume = {148}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v148/o-sullivan21a/o-sullivan21a.pdf}, url = {https://proceedings.mlr.press/v148/o-sullivan21a.html}, abstract = {3D Morphable Models have long played a key role in the construction of statistical shape models. While earlier models employed Principal Component Analysis, recent work has migrated towards mesh autoencoder models for the construction of lightweight, non-linear shape models that facilitate state-of-the-art reconstruction and the capture of high-fidelity details. Doing so results in a loss of interpretability and regularisation in the model latent space. To address this, we propose PCA retargeting, a method for expressing linear PCA models as mesh autoencoders and thereby retaining the gaussianity of the latent space. To encourage the capture of mesh details outside the expressive range of a PCA model, we introduce “free” latent space parameters. Experiments demonstrate the successful retargeting of the PCA models as mesh autoencoders. The introduction of “free” latent parameters have a greater impact when smaller latent vector sizes are used, but do not lead to any gains in reconstruction fidelity.} }
Endnote
%0 Conference Paper %T PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders %A Eimear O’ Sullivan %A Stefanos Zafeiriou %B NeurIPS 2020 Workshop on Pre-registration in Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Luca Bertinetto %E João F. Henriques %E Samuel Albanie %E Michela Paganini %E Gül Varol %F pmlr-v148-o-sullivan21a %I PMLR %P 87--99 %U https://proceedings.mlr.press/v148/o-sullivan21a.html %V 148 %X 3D Morphable Models have long played a key role in the construction of statistical shape models. While earlier models employed Principal Component Analysis, recent work has migrated towards mesh autoencoder models for the construction of lightweight, non-linear shape models that facilitate state-of-the-art reconstruction and the capture of high-fidelity details. Doing so results in a loss of interpretability and regularisation in the model latent space. To address this, we propose PCA retargeting, a method for expressing linear PCA models as mesh autoencoders and thereby retaining the gaussianity of the latent space. To encourage the capture of mesh details outside the expressive range of a PCA model, we introduce “free” latent space parameters. Experiments demonstrate the successful retargeting of the PCA models as mesh autoencoders. The introduction of “free” latent parameters have a greater impact when smaller latent vector sizes are used, but do not lead to any gains in reconstruction fidelity.
APA
O’ Sullivan, E. & Zafeiriou, S.. (2021). PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders. NeurIPS 2020 Workshop on Pre-registration in Machine Learning, in Proceedings of Machine Learning Research 148:87-99 Available from https://proceedings.mlr.press/v148/o-sullivan21a.html.

Related Material