Synthetic Image Generation for Training 2D Segmentation Models at Scale for Computer Vision Progress Monitoring in Construction-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Synthetic Image Generation for Training 2D Segmentation Models at Scale for Computer Vision Progress Monitoring in Construction

Published:2024-01-25 Issue: Volume:173 Page:273-281
ISSN:
Container-title:Computing in Civil Engineering 2023
language:
Short-container-title:

Author:

Núñez-Morales Juan D.¹²³,Hsu Shun-Hsiang¹²³,Golparvar-Fard Mani¹²³

Affiliation:

1. Ph.D. Candidate, Dept. of Civil and Environmental Engineering, Univ. of Illinois at Urbana-Champaign, Urbana, IL.

2. Ph.D. Student, Dept. of Civil and Environmental Engineering, Univ. of Illinois at Urbana-Champaign, Urbana, IL.

3. Professor of Civil and Environmental Engineering, Computer Science, and Technology Entrepreneurship, Urbana, IL.

Publisher

American Society of Civil Engineers

Link

https://ascelibrary.org/doi/pdf/10.1061/9780784485224.034

Reference13 articles.

1. Atapattu C. and Rekabdar B. (2019). “Improving the realism of synthetic images through a combination of adversarial and perceptual losses.” 2019 International Joint Con on Neural Networks (IJCNN) 1–7.

2. Optimising realism of synthetic images using cycle generative adversarial networks for improved part segmentation;Barth R.;Computers and Electronics in Agriculture,2020

3. Bi S. Sunkavalli K. Perazzi F. Shechtman E. Kim V. and Ramamoorthi R. (2020). “Deep cg2real: Synthetic-to-real translation via image disentanglement .

4. Geometry- and Appearance-Based Reasoning of Construction Progress Monitoring

5. Hong Y. Park S. and Kim H. (2020). “Synthetic data generation for indoor scene understanding using BIM.” Proceedings of the 37th ISARC 334–338 (October).

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Requirements for Parametric Design of Physics-Based Synthetic Data Generation for Learning and Inference of Defect Conditions;Construction Research Congress 2024;2024-03-18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号京ICP备18003416号-3