English

Guetzli: Perceptually Guided JPEG Encoder

Computer Vision and Pattern Recognition 2017-03-14 v1 Human-Computer Interaction

Abstract

Guetzli is a new JPEG encoder that aims to produce visually indistinguishable images at a lower bit-rate than other common JPEG encoders. It optimizes both the JPEG global quantization tables and the DCT coefficient values in each JPEG block using a closed-loop optimizer. Guetzli uses Butteraugli, our perceptual distance metric, as the source of feedback in its optimization process. We reach a 29-45% reduction in data size for a given perceptual distance, according to Butteraugli, in comparison to other compressors we tried. Guetzli's computation is currently extremely slow, which limits its applicability to compressing static content and serving as a proof- of-concept that we can achieve significant reductions in size by combining advanced psychovisual models with lossy compression techniques.

Cite

@article{arxiv.1703.04421,
  title  = {Guetzli: Perceptually Guided JPEG Encoder},
  author = {Jyrki Alakuijala and Robert Obryk and Ostap Stoliarchuk and Zoltan Szabadka and Lode Vandevenne and Jan Wassenberg},
  journal= {arXiv preprint arXiv:1703.04421},
  year   = {2017}
}
R2 v1 2026-06-22T18:44:19.826Z