# How to make a pizza: Learning a compositional layer-based GAN model

arXiv: https://arxiv.org/abs/1906.02839 · HTML: https://mlsanity.com/paper/1906.02839/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 21 of 21)

- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection](https://mlsanity.com/paper/2103.15158/) (2021)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis](https://mlsanity.com/paper/2108.12141/) (2021)
- [Amodal Completion via Progressive Mixed Context Diffusion](https://mlsanity.com/paper/2312.15540/) (2023)
- [Compositional Transformers for Scene Generation](https://mlsanity.com/paper/2111.08960/) (2021)
- [Open-World Amodal Appearance Completion](https://mlsanity.com/paper/2411.13019/) (2024)
- [Image Amodal Completion: A Survey](https://mlsanity.com/paper/2207.02062/) (2022)
- [Object-level Scene Deocclusion](https://mlsanity.com/paper/2406.07706/) (2024)
- [Learning Program Representations for Food Images and Cooking Recipes](https://mlsanity.com/paper/2203.16071/) (2022)
- [ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation](https://mlsanity.com/paper/2409.12010/) (2024)
- [Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting](https://mlsanity.com/paper/2503.21770/) (2025)
- [DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion](https://mlsanity.com/paper/2506.21544/) (2025)
- [Applications of knowledge graphs for food science and industry](https://mlsanity.com/paper/2107.05869/) (2021)
- [SynergyAmodal: Deocclude Anything with Text Control](https://mlsanity.com/paper/2504.19506/) (2025)
- [A Mobile Food Recognition System for Dietary Assessment](https://mlsanity.com/paper/2204.09432/) (2022)
- [D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation](https://mlsanity.com/paper/2212.01376/) (2022)
- [Stable Diffusion-Based Approach for Human De-Occlusion](https://mlsanity.com/paper/2508.12663/) (2025)
- [Multi-attribute Pizza Generator: Cross-domain Attribute Control with Conditional StyleGAN](https://mlsanity.com/paper/2110.11830/) (2021)
- [PHAC: Promptable Human Amodal Completion](https://mlsanity.com/paper/2603.14741/) (2026)
- [HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placement](https://mlsanity.com/paper/2604.10675/) (2026)

## Abstract (arXiv)

A food recipe is an ordered set of instructions for preparing a particular dish. From a visual perspective, every instruction step can be seen as a way to change the visual appearance of the dish by adding extra objects (e.g., adding an ingredient) or changing the appearance of the existing ones (e.g., cooking the dish). In this paper, we aim to teach a machine how to make a pizza by building a generative model that mirrors this step-by-step procedure. To do so, we learn composable module operations which are able to either add or remove a particular ingredient. Each operator is designed as a Generative Adversarial Network (GAN). Given only weak image-level supervision, the operators are trained to generate a visual layer that needs to be added to or removed from the existing image. The proposed model is able to decompose an image into an ordered sequence of layers by applying sequentially in the right order the corresponding removing modules. Experimental results on synthetic and real pizza images demonstrate that our proposed model is able to: (1) segment pizza toppings in a weaklysupervised fashion, (2) remove them by revealing what is occluded underneath them (i.e., inpainting), and (3) infer the ordering of the toppings without any depth ordering supervision. Code, data, and models are available online.