ML Anthology

Perceptually Optimized Low Bit-Rate Image Encoding

Eli Ben-David, Sharon Carmel, Boris Filippov, Dror Gill, Alexey Martemyanov, Tamar Shoham, Nikolay Terterov, Pavel Tiktov, Tom Vaughan, Alexander Zheludkov
CVPRW 2018 pp. 2610-2612
/cvprw/2018/bendavid2018cvprw-perceptually/

Abstract

In this paper we describe a system for high quality encoding of a given image set to a pre-determined, target average Bit-Per-Pixel (BPP). The proposed system uses our proprietary, patent protected, perceptual quality measure to determine the optimal allocation of bits among the images in the image set, and encodes each image using the HEVC/H.265 video encoder with a per image optimal encoding configuration and optional pre- and post-process. We employ learning methodologies both within the quality measure, and to ascertain optimal per image encoding configurations.

PDF CVPRW Semantic Scholar

Cite

Text

Ben-David et al. "Perceptually Optimized Low Bit-Rate Image Encoding." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.

Markdown

[Ben-David et al. "Perceptually Optimized Low Bit-Rate Image Encoding." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/bendavid2018cvprw-perceptually/)

BibTeX

@inproceedings{bendavid2018cvprw-perceptually,
  title     = {{Perceptually Optimized Low Bit-Rate Image Encoding}},
  author    = {Ben-David, Eli and Carmel, Sharon and Filippov, Boris and Gill, Dror and Martemyanov, Alexey and Shoham, Tamar and Terterov, Nikolay and Tiktov, Pavel and Vaughan, Tom and Zheludkov, Alexander},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {2610-2612},
  url       = {https://mlanthology.org/cvprw/2018/bendavid2018cvprw-perceptually/}
}