logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Controllable diffusion models for hazardous construction site scene generation

delete2025-06-24
delete0
PRE
AI
X
X. F. Wang
J
Jiangtao Ren
DOI：10.1016/j.asoc.2025.113446delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Two-stage LLM-diffusion framework generates construction hazard scenes. • Layout module aligns layout text attention for precise image control. • Scale fusion optimizes U-Net features to boost generation quality. • Experiments show superior controllability and quality in hazard scenes.

Journal

Applied Soft Computing cover
Applied Soft Computing
IF:
6.6
Papers:
1.4W
Citations:
4.8W

Organization

No organization information available