READ: Recursive Autoencoders for Document Layout Generation

TL;DR

READ introduces a recursive autoencoder framework that generates diverse, realistic document layouts by learning structural hierarchies, enabling large-scale layout synthesis and improving detection tasks through data augmentation.

Contribution

The paper presents a novel recursive autoencoder approach for generating plausible document layouts from learned structural hierarchies, enhancing diversity and realism.

Findings

Generated layouts are highly variable and realistic.

Layout generation improves detection performance when used for data augmentation.

The method effectively captures structural similarities among document layouts.

Abstract

Layout is a fundamental component of any graphic design. Creating large varieties of plausible document layouts can be a tedious task, requiring numerous constraints to be satisfied, including local ones relating different semantic elements and global constraints on the general appearance and spacing. In this paper, we present a novel framework, coined READ, for REcursive Autoencoders for Document layout generation, to generate plausible 2D layouts of documents in large quantities and varieties. First, we devise an exploratory recursive method to extract a structural decomposition of a single document. Leveraging a dataset of documents annotated with labeled bounding boxes, our recursive neural network learns to map the structural representation, given in the form of a simple hierarchy, to a compact code, the space of which is approximated by a Gaussian distribution. Novel hierarchies can be sampled from this space, obtaining new document layouts. Moreover, we introduce a combinatorial metric to measure structural similarity among document layouts. We deploy it to show that our method is able to generate highly variable and realistic layouts. We further demonstrate the utility of our generated layouts in the context of standard detection tasks on documents, showing that detection performance improves when the training data is augmented with generated documents whose layouts are produced by READ.