SSIM

Creator

Creator

Seonglae Cho

Created

Created

2023 Dec 15 15:22

Editor

Editor

Seonglae Cho

Edited

Edited

2023 Dec 15 15:29

Refs

Refs

Structural similarity Index (for 2D data)

notion image

Luminance - by considering average value

Contrast - by considering variance value

Structure - by considering correlation value

Loss Function

Structural similarity

The structural similarity index measure (SSIM) is a method for predicting the perceived quality of digital television and cinematic pictures, as well as other kinds of digital images and videos. SSIM is used for measuring the similarity between two images. The SSIM index is a full reference metric; in other words, the measurement or prediction of image quality is based on an initial uncompressed or distortion-free image as reference.

Structural similarity

https://en.wikipedia.org/wiki/Structural_similarity

Recommendations

/////