What is it about?
In this research study, a fully automated solution to computational rephotography is proposed based on façade segmentation of house images of different times. This proposed solution is the first fully computational solution to rephotograph using only one historical image. The proposed technique is limited to only specific types of buildings (i.e., houses with one front façade).
Featured Image
Photo by Anita Jankovic on Unsplash
Why is it important?
This research will be helpful not only for computer scientists but also for history and cultural heritage research scholars to study the social changes of a location during a specific time period, and it will allow users to go back in time to see how a specific place looked in the past.
Perspectives
I hope this "Computational Rephotography" research opens up new research challenges of fully automated rephotography of outdoor urban scenes, historical places using computer vision approaches.
Dilawar Ali
Read the Original
This page is a summary of: Single Image Façade Segmentation and Computational Rephotography of House Images Using Deep Learning, Journal on Computing and Cultural Heritage, December 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3461014.
You can read the full text:
Contributors
The following have contributed to this page
