<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><div>Hello,</div><div><br></div><div>I was recently looking for the state-of-the-art in image quality assessment models, and as best I can tell the current leading results in the literature are produced by an algorithm known as GMSD.</div><div><br></div><div>It is simple, faster than SSIM, and matches subjective human perception better than the previous best, FSIM. When you read the paper, it’s surprising it performs as well as it does: <a href="http://arxiv.org/pdf/1308.3052.pdf">http://arxiv.org/pdf/1308.3052.pdf</a></div><div><br></div><div>They do perform 2x downsampling as a pre-processing step. I don’t know how it would perform without downsampling.</div><div><br></div><div>The paper makes it sound rather impressive, so I was curious if you’d heard of it or considered using it.</div><br><div apple-content-edited="true">
<div>Brian Hempel</div></div><br></body></html>