The top image on the right is the original image. The two images directly below it were created by adding different types of distortions to the original image. The root mean squared error (RMSE) between the left distorted image and the original is smaller than the root mean squared error between the right distorted image and the original. In spite of that, the distortion is more visible in the left image. The images directly below each distorted image are the predictions of the perceptual image distortion model. Lighter areas indicate regions where the distortion is more visible while darker areas indicate regions where the distortion is less visible. The model correctly predicts that the left distorted image is more visibly distorted than the right. Click on any of the images to see them at full resolution.Model predictions of JPEG compressed images. Model of perceptual image distortion. |
|