Publication | Conference on Neural Information Processing Systems 2022
Neural Implicit Style-Net
Synthesizing shapes in a preferred style exploiting self supervision
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 publicationAbstract
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
Related Resources
2022
COIL: Constrained Optimization in Workshop on Learned Latent Space
Constrained optimization problems can be difficult because their…
2019
Unsupervised Multi-Task Feature Learning on Point Clouds
We introduce an unsupervised multi-task model to jointly learn point…
2022
UNIST: Unpaired Neural Implicit Shape Translation Network
We introduce UNIST, the first deep neural implicit modelfor…
2019
Dynamic Experience Replay
We present a novel technique called Dynamic Experience Replay (DER)…
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