Constrained Graphic Layout Generation via Latent Optimization

TL;DR

This paper introduces a method for generating graphic layouts that incorporate design semantics by optimizing in the latent space of a Transformer-based layout model, enabling constrained and flexible layout creation.

Contribution

It proposes a novel latent optimization approach for constrained graphic layout generation that can be integrated with existing models and handle explicit or implicit design constraints.

Findings

Capable of generating realistic constrained layouts

Works with both explicit and implicit design constraints

Compatible with existing layout generation models

Abstract

It is common in graphic design humans visually arrange various elements according to their design intent and semantics. For example, a title text almost always appears on top of other elements in a document. In this work, we generate graphic layouts that can flexibly incorporate such design semantics, either specified implicitly or explicitly by a user. We optimize using the latent space of an off-the-shelf layout generation model, allowing our approach to be complementary to and used with existing layout generation models. Our approach builds on a generative layout model based on a Transformer architecture, and formulates the layout generation as a constrained optimization problem where design constraints are used for element alignment, overlap avoidance, or any other user-specified relationship. We show in the experiments that our approach is capable of generating realistic layouts in both constrained and unconstrained generation tasks with a single model. The code is available at https://github.com/ktrk115/const_layout .