We developed a foundation for assessing visual quality with “corrupted reference” (CR-QA)—a new quality assessment (QA) paradigm for reasoning about human vision and image restoration problems jointly. In most image restoration problems, the notion of an ideal reference that exist only in theory and not in practice. CR-QA assesses the visual quality of a restored image signal relative to this ideal reference image (not provided) with the help of observed image (i.e. corrupted reference). This is in contrast to today’s QAs, which either require direct access to the ideal reference image (full-reference QA) or disregards the ideal reference entirely (no-reference QA).

Zhang, Chen; Hirakawa, Keigo (2014): Blind Full Reference Quality Assessment Of Poisson Image Denoising. In: IEEE International Conference on Image Processing, 2014. (Type: Inproceeding | Links | BibTeX)
Cheng,; Hirakawa., (2012): Corrupted Reference Image Quality Assessment. In: Image Processing (ICIP), 2012 19th IEEE International Conference on, 2012. (Type: Inproceeding | Links | BibTeX)