Publication | Conference on Neural Information Processing Systems 2022

Neural Implicit Style-Net

Synthesizing shapes in a preferred style exploiting self supervision

Examples of style transfer results

This paper introduces a completely new way for defining 3D style using a 3D transformation that destroys style but preserve content. Given such a transformation we can learn and disentangling style from content in unsupervised learning setting, enabling 3D style transfer with minimum number of examples.

Download publication

Abstract

Neural Implicit Style-Net: Synthesizing shapes in a preferred style exploiting self supervision

Marco Fumero, Hooman Shayani, Aditya Sanghi, Emanuele Rodolà

Conference on Neural Information Processing Systems 2022

We introduce a novel approach to disentangle style from content in the 3D domain and perform unsupervised neural style transfer. Our approach is able to extract style information from 3D input in a self supervised fashion, conditioning the definition of style on inductive biases enforced explicitly, in the form of specific augmentations applied to the input. This allows, at test time, to select specifically the features to be transferred between two arbitrary 3D shapes, being still able to capture complex changes (e.g. combinations of arbitrary geometrical and topological transformations) with the data prior. Coupled with the choice of representing 3D shapes as neural implicit fields, we are able to perform style transfer in a controllable way, handling a variety of transformations. We validate our approach qualitatively and quantitatively on a dataset with font style labels.

Associated Researchers

Marco Fumero

Sapienza University of Rome

Emanuele Rodolà

Sapienza University of Rome

View all researchers

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us