CVOct 22, 2021

Multi-attribute Pizza Generator: Cross-domain Attribute Control with Conditional StyleGAN

arXiv:2110.11830v1
Originality Incremental advance
AI Analysis

This addresses a challenging computer vision problem for image synthesis applications, but it is incremental as it builds on StyleGAN2 with domain-specific adaptations.

The paper tackled multi-attribute conditional image generation by proposing MPG, a GAN framework that synthesizes pizza images with controlled ingredients and view attributes, achieving photo-realistic results beyond the training data range.

Multi-attribute conditional image generation is a challenging problem in computervision. We propose Multi-attribute Pizza Generator (MPG), a conditional Generative Neural Network (GAN) framework for synthesizing images from a trichotomy of attributes: content, view-geometry, and implicit visual style. We design MPG by extending the state-of-the-art StyleGAN2, using a new conditioning technique that guides the intermediate feature maps to learn multi-scale multi-attribute entangled representationsof controlling attributes. Because of the complex nature of the multi-attribute image generation problem, we regularize the image generation by predicting the explicit conditioning attributes (ingredients and view). To synthesize a pizza image with view attributesoutside the range of natural training images, we design a CGI pizza dataset PizzaView using 3D pizza models and employ it to train a view attribute regressor to regularize the generation process, bridging the real and CGI training datasets. To verify the efficacy of MPG, we test it on Pizza10, a carefully annotated multi-ingredient pizza image dataset. MPG can successfully generate photo-realistic pizza images with desired ingredients and view attributes, beyond the range of those observed in real-world training data.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes