Benchmarking JPEG XL image compression

Abstract

JPEG XL is a practical, royalty-free codec for scalable web distribution and efficient compression of high-quality photographs. It also includes previews, progressiveness, animation, transparency, high dynamic range, wide color gamut, and high bit depth. Users expect faithful reproductions of ever higher-resolution images. Experiments performed during standardization have shown the feasibility of economical storage without perceptible quality loss, lossless transcoding of existing JPEG, and fast software encoders and decoders. We analyse the results of subjective and objective evaluations versus existing codecs including HEVC and JPEG. New image codecs have to co-exist with their previous generations for several years. JPEG XL is unique in providing value for both existing JPEGs as well as new users. It includes coding tools to reduce the transmission and storage costs of JPEG by 22% while allowing byte-for-byte exact reconstruction of the original JPEG. Avoiding transcoding and additional artifacts helps to preserve our digital heritage. Applications require fast and low-power decoding. JPEG XL was designed to benefit from multicore and SIMD, and actually decodes faster than JPEG. We report the resulting speeds on ARM and x86 CPUs. To enable reproduction of these results, we open sourced the JPEG XL software in 2019.

An Integrated Representation & Compression Scheme Based on Convolutional Autoencoders with 4D DCT Perceptual Encoding for High Dynamic Range Light Fields

“…The performance of the proposed scheme 4DDCT-UCS is compared with JPEG-XL Alakuijala et al [2020] and UCS Mukherjee et al [2018]. In Fig 3a, the analysis of the comparison in terms of rate-distortion is depicted.…”

“…High Efficiency Video Coding (HEVC) Sullivan et al [2012] is used to achieve additional encoding by reducing the inter-frame, intra-frame and other intrinsic redundancies present in the light field. The performance of the proposed scheme is being compared with JPEG-XL Alakuijala et al [2020] and ours is significantly superior. It is inferred from the experimental results provided in section 3 that our proposed algorithm is capable of capturing and high-quality reconstruction of HDR light field from a reduced number of acquired images.…”

Comprehensive assessment of image compression algorithms

“…Another attempt to cope with the plethora of JPEG images distributed over global computer networks and stored on private consumer devices has been proposed by JPEG XL. 22,23 This emerging standard, which is undergoing the final steps of standardization, features numerically lossless transcoding of images that are already compressed with JPEG. JPEG XL can save up to 22% 22 in bit rate or in storage when numerically lossless transcoding is applied to images compressed with JPEG, while preserving exactly the same visual quality.…”

Comparison of Lossless Image Formats

“…JPEG XL (2020) [1,2] is a new image format that supports both lossy and lossless compression. ISO/IEC standard is still under development.…”