Optimizing Multiscale SSIM for Compression via MLDS (original) (raw)

CID22: Large-Scale Subjective Quality Assessment for High Fidelity Image Compression

We propose a new methodology for large-scale subjective quality assessment of compressed still images in the high fidelity range. Combining two different assessment protocols, one based on pairwise comparisons, the other on absolute opinions, it is designed to assess this range of qualities not well-covered by previous methodologies. The methodology was applied to create the Cloudinary Image Dataset '22 (CID22), consisting of 22,153 annotated images (with scores based on 1.4 million opinions), originating from 250 pristine images compressed using JPEG, JPEG 2000, JPEG XL, HEIC, WebP, and AVIF at high fidelity settings. Using this data, we evaluate various image encoders and objective metrics.

Human Perceptual Evaluations for Image Compression

2019

Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG). A standard way of comparing image compression schemes today is to use perceptual similarity metrics such as PSNR or MS-SSIM (multi-scale structural similarity). This has led to some deep learning techniques which directly optimize for MS-SSIM by choosing it as a loss function. While this leads to a higher MS-SSIM for such techniques, we demonstrate using user studies that the resulting improvement may be misleading. Deep learning techniques for image compression with a higher MS-SSIM may actually be perceptually worse than engineered compression schemes with a lower MS-SSIM.

Subjective Assessment of Objective Image Quality Metrics Range Guaranteeing Visually Lossless Compression

Sensors

The usage of media such as images and videos has been extensively increased in recent years. It has become impractical to store images and videos acquired by camera sensors in their raw form due to their huge storage size. Generally, image data is compressed with a compression algorithm and then stored or transmitted to another platform. Thus, image compression helps to reduce the storage size and transmission cost of the images and videos. However, image compression might cause visual artifacts, depending on the compression level. In this regard, performance evaluation of the compression algorithms is an essential task needed to reconstruct images with visually or near-visually lossless quality in case of lossy compression. The performance of the compression algorithms is assessed by both subjective and objective image quality assessment (IQA) methodologies. In this paper, subjective and objective IQA methods are integrated to evaluate the range of the image quality metrics (IQMs) ...