paper-with-me

Papers

3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces

2021-11-24 · CVPR 2022 1 · Simone Foti, Bongjin Koo, Danail Stoyanov, Matthew J. Clarkson

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this paper, we propose an intuitive yet effective self-supervised approach to train a 3D shape variational autoencoder (VAE) which encourages a disentangled latent representation of identity features. Curating the mini-batch generation by swapping arbitrary features across different shapes allows to define a loss function leveraging known differences and similarities in the latent representations. Experimental results conducted on 3D meshes show that state-of-the-art methods for latent disentanglement are not able to disentangle identity features of faces and bodies. Our proposed method properly decouples the generation of such features while maintaining good representation and reconstruction capabilities.

📄 PDF Abstract BibTeX arXiv:2111.12448

Code (1)

simofoti/3dvae-swapdisentangled 공식 구현 pytorch

Tasks

Disentanglement

Similar Papers 제목 키워드 기반

Variantional autoencoder with decremental information bottleneck for disentanglement

2023-03-22 · Jiantao Wu, Shentong Mo, Muhammad Awais, Sara Atito 외

One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase the information bottleneck during train…

DisentanglementRepresentation Learning

Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement

2021-05-19 · Guillaume Carbajal, Julius Richter, Timo Gerkmann

Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been cond…

AttributeDecoderDisentanglementSpeech Enhancement

3D Generative Model Latent Disentanglement via Local Eigenprojection

2023-02-24 · Simone Foti, Bongjin Koo, Danail Stoyanov, Matthew J. Clarkson

Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attrib…

AttributeDisentanglementmodel

Geometric Disentanglement for Generative Latent Shape Models

2019-08-18 · ICCV 2019 10 · Tristan Aumentado-Armstrong, Stavros Tsogkas, Allan Jepson, Sven Dickinson

Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent repre…

3D Object Retrieval3D Shape Generation3D Shape RepresentationDisentanglement+2

Latent feature disentanglement for 3D meshes

2019-06-07 · Jake Levinson, Avneesh Sud, Ameesh Makadia

Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional V…

Disentanglement