Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

arXiv:2311.13602v2 Announce Type: replace
Abstract: Content-aware graphic layout generation aims to automatically arrange visual elements along with a given content, such as an e-commerce product image. In this paper, we argue that the current layout generation approaches suffer from the limited training data for the high-dimensional layout structure. We show that a simple retrieval augmentation can significantly improve the generation quality. Our model, which is named Retrieval-Augmented Layout Transformer (RALF), retrieves nearest neighbor layout examples based on an input image …

abstract arxiv commerce cs.cv current data e-commerce image paper product retrieval retrieval-augmented show simple training training data transformer type visual