CNN-Based Cross-Dataset No-Reference Image Quality Assessment

Dan Yang, Veli-Tapani Peltoketo, Joni-Kristian Kamarainen; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0


Recent works on no-reference image quality assessment (NR-IQA) have reported good performance for various datasets. However, they suffer from significant performance drops in cross-dataset evaluations which indicates poor generalization power. We propose a Siamese architecture and training procedures for cross-dataset deep NR-IQA that achieves clearly better performance. Moreover, we show that the architecture can be further boosted by i) pre-training with a large aesthetics dataset and ii) adding low-level quality cues, sharpness, tone and colourfulness, as additional features.

Related Material

author = {Yang, Dan and Peltoketo, Veli-Tapani and Kamarainen, Joni-Kristian},
title = {CNN-Based Cross-Dataset No-Reference Image Quality Assessment},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}