ML Anthology

Lossy GIF Compression Using Deep Intrinsic Parameterization

Anuj Pahuja, Simon Lucey
ICCVW 2019 pp. 4581-4583
doi:10.1109/ICCVW.2019.00559 /iccvw/2019/pahuja2019iccvw-lossy/

Abstract

With billions of animated GIFs being shared and viewed every day, it has become imperative for GIF hosting websites to serve content with minimal lag. To cater to the ever-decreasing attention span of a wide audience with different connectivity issues, it makes sense to suitably compress GIFs during transmission. We present a unique and interpretable approach to lossily compress GIFs or any temporal sequence of frames through a CNN based image parameterization technique and a simple scalar quantization scheme. Contrary to learned compression techniques, our approach is instance-specific and self-supervised.

ICCVW Semantic Scholar

Cite

Text

Pahuja and Lucey. "Lossy GIF Compression Using Deep Intrinsic Parameterization." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00559

Markdown

[Pahuja and Lucey. "Lossy GIF Compression Using Deep Intrinsic Parameterization." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/pahuja2019iccvw-lossy/) doi:10.1109/ICCVW.2019.00559

BibTeX

@inproceedings{pahuja2019iccvw-lossy,
  title     = {{Lossy GIF Compression Using Deep Intrinsic Parameterization}},
  author    = {Pahuja, Anuj and Lucey, Simon},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {4581-4583},
  doi       = {10.1109/ICCVW.2019.00559},
  url       = {https://mlanthology.org/iccvw/2019/pahuja2019iccvw-lossy/}
}