一句话：提出神经符号DSL与程序合成方法，从用户演示自动生成细粒度批量图像编辑程序。
本文提出一种基于程序合成的批量图像处理方法，支持对图像中满足特定属性的单个对象进行细粒度编辑，而不仅限于全局操作。为表达此类任务，作者设计了一种神经符号领域特定语言（DSL），将预训练图像分类网络与用于符号推理的语言构造相结合。系统ImageEye能从用户演示中自动学习该DSL程序，其核心是一种新的合成算法。作者在50个图像编辑任务上评估，96%的任务可被自动化完成。
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.
@article{paperbot1979,
title = {ImageEye: Batch Image Processing using Program Synthesis},
author = {Celeste Barnaby and Qiaochu Chen and Roopsha Samanta and Işıl Dillig},
journal = {Proceedings of the ACM on Programming Languages},
volume = {7},
number = {PLDI},
year = {2023},
doi = {10.1145/3591248}
}