Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

6 Dec 2016Sebastian BosseDominique ManiryKlaus-Robert MüllerThomas WiegandWojciech Samek

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.