Graph-based Deep Generative Modelling for Document Layout Generation

TL;DR

This paper introduces a novel graph neural network-based deep generative model that creates realistic synthetic document layouts, aiding in training document interpretation systems, especially for administrative documents like invoices.

Contribution

It presents the first graph-based approach for document layout generation, specifically applied to administrative document images such as invoices.

Findings

Successfully generated diverse, plausible document layouts

Enhanced training data for document interpretation systems

First application of GNNs in document layout synthesis

Abstract

One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, the principal information of its content is stored in the layout itself. In this work, we have proposed an automated deep generative model using Graph Neural Networks (GNNs) to generate synthetic data with highly variable and plausible document layouts that can be used to train document interpretation systems, in this case, specially in digital mailroom applications. It is also the first graph-based approach for document layout generation task experimented on administrative document images, in this case, invoices.