LayoutFlow: Flow Matching for Layout Generation

Autor:	Guerreiro, Julian Jorge Andrade, Inoue, Naoto, Masui, Kento, Otani, Mayu, Nakayama, Hideki
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alternative to current diffusion-based layout generation models. Specifically, we propose LayoutFlow, an efficient flow-based model capable of generating high-quality layouts. Instead of progressively denoising the elements of a noisy layout, our method learns to gradually move, or flow, the elements of an initial sample until it reaches its final prediction. In addition, we employ a conditioning scheme that allows us to handle various generation tasks with varying degrees of conditioning with a single model. Empirically, LayoutFlow performs on par with state-of-the-art models while being significantly faster. Comment: Accepted to ECCV 2024, Project Page: https://julianguerreiro.github.io/layoutflow/
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.18187 Zobrazit plný text záznamu View this record from Arxiv