FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance

A paper titled "FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance" proposes a reference-based image quality assessment (IQA) metric that measures the perceptual distance between a pair of images by examining the forking moment in a generative trajectory, rather than relying on human-annotated mean opinion score (MOS) data as recent reference-based IQA metrics do. The work targets how the human visual system (HVS) operates in judging image quality.

Reference-based image quality assessment IQA metrics aim to reflect how humans perceive the perceptual distance between a pair of images. To learn how the human visual system HVS operates, recent reference-based IQA metrics heavily rely on human-annotated data. Mean opinion score MOS -based poi