ChatPattern: Layout Pattern Customization via Natural Language

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Zixiao, Shen, Yunheng, Yao, Xufeng, Zhao, Wenqian, Bai, Yang, Farnia, Farzan, Yu, Bei
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911810441969664
author Wang, Zixiao
Shen, Yunheng
Yao, Xufeng
Zhao, Wenqian
Bai, Yang
Farnia, Farzan
Yu, Bei
author_facet Wang, Zixiao
Shen, Yunheng
Yao, Xufeng
Zhao, Wenqian
Bai, Yang
Farnia, Farzan
Yu, Bei
contents Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention. In this paper, we propose ChatPattern, a novel Large-Language-Model (LLM) powered framework for flexible pattern customization. ChatPattern utilizes a two-part system featuring an expert LLM agent and a highly controllable layout pattern generator. The LLM agent can interpret natural language requirements and operate design tools to meet specified needs, while the generator excels in conditional layout generation, pattern modification, and memory-friendly patterns extension. Experiments on challenging pattern generation setting shows the ability of ChatPattern to synthesize high-quality large-scale patterns.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15434
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatPattern: Layout Pattern Customization via Natural Language
Wang, Zixiao
Shen, Yunheng
Yao, Xufeng
Zhao, Wenqian
Bai, Yang
Farnia, Farzan
Yu, Bei
Computation and Language
Artificial Intelligence
Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention. In this paper, we propose ChatPattern, a novel Large-Language-Model (LLM) powered framework for flexible pattern customization. ChatPattern utilizes a two-part system featuring an expert LLM agent and a highly controllable layout pattern generator. The LLM agent can interpret natural language requirements and operate design tools to meet specified needs, while the generator excels in conditional layout generation, pattern modification, and memory-friendly patterns extension. Experiments on challenging pattern generation setting shows the ability of ChatPattern to synthesize high-quality large-scale patterns.
title ChatPattern: Layout Pattern Customization via Natural Language
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.15434