Perceptual Constancy Constrained Single Opinion Score Calibration for Image Quality Assessment
This work addresses the challenge of limited annotation data for image quality assessment, offering an incremental improvement in efficiency for researchers and practitioners in computer vision.
The paper tackles the problem of estimating an image's mean opinion score (MOS) from a single opinion score (SOS) by formulating it as a maximum likelihood estimation with perceptual correlation constraints, resulting in a method that efficiently calibrates biased SOS and significantly improves image quality assessment model learning when only SOSs are available.
In this paper, we propose a highly efficient method to estimate an image's mean opinion score (MOS) from a single opinion score (SOS). Assuming that each SOS is the observed sample of a normal distribution and the MOS is its unknown expectation, the MOS inference is formulated as a maximum likelihood estimation problem, where the perceptual correlation of pairwise images is considered in modeling the likelihood of SOS. More specifically, by means of the quality-aware representations learned from the self-supervised backbone, we introduce a learnable relative quality measure to predict the MOS difference between two images. Then, the current image's maximum likelihood estimation towards MOS is represented by the sum of another reference image's estimated MOS and their relative quality. Ideally, no matter which image is selected as the reference, the MOS of the current image should remain unchanged, which is termed perceptual cons tancy constrained calibration (PC3). Finally, we alternatively optimize the relative quality measure's parameter and the current image's estimated MOS via backpropagation and Newton's method respectively. Experiments show that the proposed method is efficient in calibrating the biased SOS and significantly improves IQA model learning when only SOSs are available.