Deep Perceptual Image Quality Assessment for Compression
Juan Carlos Mier, Eddie Huang, Hossein Talebi, Feng Yang, Peyman, Milanfar

TL;DR
This paper introduces a large dataset of human perceptual preferences for lossy image compression and develops a deep learning-based quality metric that outperforms existing methods and generalizes well to unseen data.
Contribution
The paper presents the largest dataset for perceptual image quality assessment and a novel deep learning metric that surpasses current state-of-the-art methods.
Findings
The new dataset enables effective training of deep models for image quality assessment.
The proposed metric outperforms traditional and learning-based existing methods.
The model generalizes well to unseen datasets of human perceptual preferences.
Abstract
Lossy Image compression is necessary for efficient storage and transfer of data. Typically the trade-off between bit-rate and quality determines the optimal compression level. This makes the image quality metric an integral part of any imaging system. While the existing full-reference metrics such as PSNR and SSIM may be less sensitive to perceptual quality, the recently introduced learning methods may fail to generalize to unseen data. In this paper we propose the largest image compression quality dataset to date with human perceptual preferences, enabling the use of deep learning, and we develop a full reference perceptual quality assessment metric for lossy image compression that outperforms the existing state-of-the-art methods. We show that the proposed model can effectively learn from thousands of examples available in the new dataset, and consequently it generalizes better to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
