# Synthesizing Programs for Images using Reinforced Adversarial Learning

arXiv: https://arxiv.org/abs/1804.01118 · HTML: https://mlsanity.com/paper/1804.01118/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2018.

## Built on by (most cited first, 30 of 72)

- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [Learning to Understand Goal Specifications by Modelling Reward](https://mlsanity.com/paper/1806.01946/) (2018)
- [Paint Transformer: Feed Forward Neural Painting with Stroke Prediction](https://mlsanity.com/paper/2108.03798/) (2021)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [CLIPasso: Semantically-Aware Object Sketching](https://mlsanity.com/paper/2202.05822/) (2022)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes](https://mlsanity.com/paper/2103.17185/) (2021)
- [Adversarial Intrinsic Motivation for Reinforcement Learning](https://mlsanity.com/paper/2105.13345/) (2021)
- [Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts](https://mlsanity.com/paper/2109.08857/) (2021)
- [Content and Style Aware Generation of Text-line Images for Handwriting Recognition](https://mlsanity.com/paper/2204.05539/) (2022)
- [Can Large Language Models Understand Symbolic Graphics Programs?](https://mlsanity.com/paper/2408.08313/) (2024)
- [SketchAgent: Language-Driven Sequential Sketch Generation](https://mlsanity.com/paper/2411.17673/) (2024)
- [Neural-Sim: Learning to Generate Training Data with NeRF](https://mlsanity.com/paper/2207.11368/) (2022)
- [Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation](https://mlsanity.com/paper/2305.00909/) (2023)
- [Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data](https://mlsanity.com/paper/2112.00054/) (2021)
- [TikZero: Zero-Shot Text-Guided Graphics Program Synthesis](https://mlsanity.com/paper/2503.11509/) (2025)
- [Differentiable Drawing and Sketching](https://mlsanity.com/paper/2103.16194/) (2021)
- [Contrastive Active Inference](https://mlsanity.com/paper/2110.10083/) (2021)
- [Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning](https://mlsanity.com/paper/2110.15481/) (2021)
- [DoodleFormer: Creative Sketch Drawing with Transformers](https://mlsanity.com/paper/2112.03258/) (2021)
- [NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation](https://mlsanity.com/paper/2405.15217/) (2024)
- [NeuralSVG: An Implicit Representation for Text-to-Vector Generation](https://mlsanity.com/paper/2501.03992/) (2025)
- [Cloud2Curve: Generation and Vectorization of Parametric Sketches](https://mlsanity.com/paper/2103.15536/) (2021)
- [Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region](https://mlsanity.com/paper/2309.03504/) (2023)
- [Neural Strokes: Stylized Line Drawing of 3D Shapes](https://mlsanity.com/paper/2110.03900/) (2021)

## Abstract (arXiv)

Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets. To mitigate these issues, we present SPIRAL, an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images. The goal of this agent is to fool a discriminator network that distinguishes between real and rendered data, trained with a distributed reinforcement learning setup without any supervision. A surprising finding is that using the discriminator's output as a reward signal is the key to allow the agent to make meaningful progress at matching the desired output rendering. To the best of our knowledge, this is the first demonstration of an end-to-end, unsupervised and adversarial inverse graphics agent on challenging real world (MNIST, Omniglot, CelebA) and synthetic 3D datasets.