Text2Street: Controllable Text-to-image Generation for Street Views

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Jinming, Gu, Songen, Duan, Yiting, Chen, Xingyue, Luo, Junfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929236221100032
author Su, Jinming
Gu, Songen
Duan, Yiting
Chen, Xingyue
Luo, Junfeng
author_facet Su, Jinming
Gu, Songen
Duan, Yiting
Chen, Xingyue
Luo, Junfeng
contents Text-to-image generation has made remarkable progress with the emergence of diffusion models. However, it is still a difficult task to generate images for street views based on text, mainly because the road topology of street scenes is complex, the traffic status is diverse and the weather condition is various, which makes conventional text-to-image models difficult to deal with. To address these challenges, we propose a novel controllable text-to-image framework, named \textbf{Text2Street}. In the framework, we first introduce the lane-aware road topology generator, which achieves text-to-map generation with the accurate road structure and lane lines armed with the counting adapter, realizing the controllable road topology generation. Then, the position-based object layout generator is proposed to obtain text-to-layout generation through an object-level bounding box diffusion strategy, realizing the controllable traffic object layout generation. Finally, the multiple control image generator is designed to integrate the road topology, object layout and weather description to realize controllable street-view image generation. Extensive experiments show that the proposed approach achieves controllable street-view text-to-image generation and validates the effectiveness of the Text2Street framework for street views.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04504
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text2Street: Controllable Text-to-image Generation for Street Views
Su, Jinming
Gu, Songen
Duan, Yiting
Chen, Xingyue
Luo, Junfeng
Computer Vision and Pattern Recognition
Text-to-image generation has made remarkable progress with the emergence of diffusion models. However, it is still a difficult task to generate images for street views based on text, mainly because the road topology of street scenes is complex, the traffic status is diverse and the weather condition is various, which makes conventional text-to-image models difficult to deal with. To address these challenges, we propose a novel controllable text-to-image framework, named \textbf{Text2Street}. In the framework, we first introduce the lane-aware road topology generator, which achieves text-to-map generation with the accurate road structure and lane lines armed with the counting adapter, realizing the controllable road topology generation. Then, the position-based object layout generator is proposed to obtain text-to-layout generation through an object-level bounding box diffusion strategy, realizing the controllable traffic object layout generation. Finally, the multiple control image generator is designed to integrate the road topology, object layout and weather description to realize controllable street-view image generation. Extensive experiments show that the proposed approach achieves controllable street-view text-to-image generation and validates the effectiveness of the Text2Street framework for street views.
title Text2Street: Controllable Text-to-image Generation for Street Views
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.04504