A no-reference metric for evaluating the quality of motion deblurring

114 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Perception-Distortion Tradeoff (2017, background): “blind deblurring with large blurs [62], [63]), the perceptual metric should be humanopinion-scores or the loss of a discriminator trained to distinguish the algorithms’ outputs from natural images.”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “On the other hand, since SR images usually contain blur and ringing artifacts, the proposed algorithm bears some resemblance to existing metrics for blur and sharpness estimation [29, 30, 31].”
A Comparative Study for Single Image Blind Deblurring (2016, methodology): “First, the goal of [20] is to learn a no-reference metric from the collected perceptual scores while our objective is the performance comparison of state-of-the-art deblurring algorithms on the real-world images.”
Learning a Discriminative Model for the Perception of Realism in Composite Images (2015, unknown): “Other methods take a discriminative approach [9, 17, 25, 27, 33].”