Towards User-Friendly Image Inpainting: Learning-to-Rank based Image Quality Assessment for Image Inpainting

Add to your list(s) Download to your calendar using vCal

• Mariko Isogawa (NTT Media Intelligence Laboratories)
• Friday 08 September 2017, 11:00-12:00
• CBL Room BE-438, Department of Engineering.

If you have a question about this talk, please contact zoubin-office.

This talk has been canceled/deleted

Image inpainting, which removes and restores unwanted regions in images, is widely acknowledged as a task whose results vary largely depending on the parameter settings. In typical use cases, users have to choose parameters and observe the results by trial and error, until the desired results are obtained. Thus a way to automatically select the best result is needed. In this talk, I will introduce our current research for learning based image quality assessment (IQA) methods for inpainting to support this need. Our framework uses no subjectively annotated data; we use only simulated failure results of inpainted images whose subjective qualities are controlled as the training data.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.