# ImageEye: Batch Image Processing Using Program Synthesis

arXiv: https://arxiv.org/abs/2304.03253 · HTML: https://mlsanity.com/paper/2304.03253/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 83 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 21 of 21)

- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Inferring and Executing Programs for Visual Reasoning](https://mlsanity.com/paper/1705.03633/) (2017)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [Neural Photo Editing with Introspective Adversarial Networks](https://mlsanity.com/paper/1609.07093/) (2016)
- [Neural Programmer-Interpreters](https://mlsanity.com/paper/1511.06279/) (2015)
- [Foreground-aware Image Inpainting](https://mlsanity.com/paper/1901.05945/) (2019)
- [Learning to Infer Graphics Programs from Hand-Drawn Images](https://mlsanity.com/paper/1707.09627/) (2017)
- [Learning to Infer and Execute 3D Shape Programs](https://mlsanity.com/paper/1901.02875/) (2019)
- [Non-Stationary Texture Synthesis by Adversarial Expansion](https://mlsanity.com/paper/1805.04487/) (2018)
- [Program Synthesis using Conflict-Driven Learning](https://mlsanity.com/paper/1711.08029/) (2017)
- [Modular Generative Adversarial Networks](https://mlsanity.com/paper/1804.03343/) (2018)
- [Optimal Neural Program Synthesis from Multimodal Specifications](https://mlsanity.com/paper/2010.01678/) (2020)
- [Multi-modal Synthesis of Regular Expressions](https://mlsanity.com/paper/1908.03316/) (2019)
- [Learning Neurosymbolic Generative Models via Program Synthesis](https://mlsanity.com/paper/1901.08565/) (2019)
- [Component-based Synthesis of Table Consolidation and Transformation Tasks from Examples](https://mlsanity.com/paper/1611.07502/) (2016)
- [WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstration](https://mlsanity.com/paper/2203.09993/) (2022)
- [Iterative Program Synthesis for Adaptable Social Navigation](https://mlsanity.com/paper/2103.04880/) (2021)
- [Synthesizing Analytical SQL Queries from Computation Demonstration](https://mlsanity.com/paper/2204.07102/) (2022)
- [Automated Migration of Hierarchical Data to Relational Tables using Programming-by-Example](https://mlsanity.com/paper/1711.04001/) (2017)

## Built on by (most cited first, 4 of 4)

- [Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction](https://mlsanity.com/paper/2405.15912/) (2024)
- [VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction](https://mlsanity.com/paper/2407.06826/) (2024)
- [Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with B'ezier Curves](https://mlsanity.com/paper/2511.00076/) (2025)
- [MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents](https://mlsanity.com/paper/2608.07533/) (2026)

## Abstract (arXiv)

This paper presents a new synthesis-based approach for batch image processing. Unlike existing tools that can only apply global edits to the entire image, our method can apply fine-grained edits to individual objects within the image. For example, our method can selectively blur or crop specific objects that have a certain property. To facilitate such fine-grained image editing tasks, we propose a neuro-symbolic domain-specific language (DSL) that combines pre-trained neural networks for image classification with other language constructs that enable symbolic reasoning. Our method can automatically learn programs in this DSL from user demonstrations by utilizing a novel synthesis algorithm. We have implemented the proposed technique in a tool called ImageEye and evaluated it on 50 image editing tasks. Our evaluation shows that ImageEye is able to automate 96% of these tasks.