mlsanityData to 14 Oct 2026

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

arXiv 2110.11830 ↗First posted 22 Oct 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 22 Oct 2021.

Builds on

24 of 33 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  8. 2014Conditional Generative Adversarial Netscited by 2,162
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  10. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  12. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
12 more
  1. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  2. 2020Closed-Form Factorization of Latent Semantics in GANscited by 408
  3. 2018cGANs with Projection Discriminatorcited by 254
  4. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 242
  5. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  6. 2019Controllable Text-to-Image Generationcited by 187
  7. 2019MirrorGAN: Learning Text-to-image Generation by Redescriptioncited by 176
  8. 2021GAN-Control: Explicitly Controllable GANscited by 91
  9. 2019How to make a pizza: Learning a compositional layer-based GAN modelcited by 21
  10. 2020CookGAN: Meal Image Synthesis from Ingredientscited by 14
  11. 2019LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networkscited by 5
  12. 2019GILT: Generating Images from Long Textcited by 2

Built on by

Not cited yet.