F Mean Squared Error: Love It or Leave It?
By A. Bovik. 2009
Subfields: Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Evaluation & Benchmarks
- Aäron van den Oord
- Satyam Bhardwaj
- Prateek Gupta
- Djemel Ziou
- Matthias Bethge
- Vikrant Bhateja
- Alain Horé
- Lucas Theis
Citations in the corpus
- A note on the evaluation of generative models (2015, background): “But already perceptually small changes can lead to large changes in Euclidean distance, as is well known in the psychophysics literature (e.g., Wang & Bovik, 2009).”
- A modified PSNR metric based on HVS for quality assessment of color images (2011, background): “There are cases when their values saturate to yield similar results with different types of distortions [3].”
- Image Quality Metrics: PSNR vs. SSIM (2010, background): “The MSE in equation (2) can be rewritten as: ( )22 2 2f g fg f gMSE σ σ σ μ μ= + − + − (5) where σ2f and σ2g are the variances of images f and g, and σfg the covariance between f and g: ( )22 1 1 1 M N f ij f i j f MN σ μ = = = −∑∑ , ( ) ( ) 1 1 1 M N fg ij f ij g i j f g MN σ μ μ = = = − −∑∑ (6) Th”