Controllable diffusion models for hazardous construction site scene generation

doi:10.1016/j.asoc.2025.113446

2025-06-24

PRE

X. F. Wang

Jiangtao Ren

DOI：10.1016/j.asoc.2025.113446

原文链接

原文求助

摘要

En 中文

• 两阶段LLM-diffusion框架生成施工危险场景。 • 布局模块对齐布局文本注意力以实现精确图像控制。 • 尺度融合优化U-Net特征以提升生成质量。 • 实验表明在危险场景中具有更优的可控性和质量。

期刊

Applied Soft Computing

IF:

6.6

论文数:

1.4W

被引数:

4.8W

机构

暂无机构信息

引用论文

Automated annotation for visual recognition of construction resources using synthetic images 使用合成图像对建筑资源进行视觉识别的自动注释

AUTOMATION IN CONSTRUCTION

IF11.5

2016-02-01

PREAI

Soltani, Mohammad Mostafa; Zhu, Zhenhua; Hammad, Amin

A Style-Based Generator Architecture for Generative Adversarial Networks 生成对抗网络的基于样式的生成器体系结构

IEEE Transactions on Pattern Analysis and Machine Intelligence

IF0

2021-12-01

PREAI

Tero Karras; Samuli Laine; Timo Aila

MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2024-06-16

PREAI

Dewei Zhou; You Li; Fan Ma; Xiaoting Zhang; Yi Yang

Conditional Generative Adversarial Networks with Adversarial Attack and Defense for Generative Data Augmentation

Journal of Computing in Civil Engineering

IF0

2022-05-01

PREAI

Francis Baek; Daeho Kim; Somin Park; Hyoungkwan Kim; SangHyun Lee

Image generation of hazardous situations in construction sites using text-to-image generative model for training deep neural networks 使用用于训练深度神经网络的文本到图像生成模型生成建筑工地危险情况的图像

AUTOMATION IN CONSTRUCTION

IF11.5

2024-10-01

PREAI

Kim, Hayoung; Yi, June-Seong

Dataset and benchmark for detecting moving objects in construction sites 用于检测建筑工地中移动物体的数据集和基准

AUTOMATION IN CONSTRUCTION

IF11.5

2021-02-01

PREAI

An Xuehui; Zhou Li; Liu Zuguang; Wang Chengzhi; Li Pengfei; Li Zhiwei

没有更多内容