Adapting JPEG XS gains and priorities to tasks and contents

Brummer, Benoit;De Vleeschouwer, Christophe
(2020) IEEE/CVF Conference on Computer Vision and Pattern Recognition — Location: Seattle (14.June.2020)

Files

Adapting_JPEG_XS_gains_and_priorities_to_tasks_and_contents.pdf
  • Open Access
  • Adobe PDF
  • 1.18 MB
Download

Details

Authors
Abstract
Most current research in the domain of image compression focuses solely on achieving state of the art compression ratio, but that is not always usable in today’s workflow due to the constraints on computing resources. Constant market requirements for a low-complexity image codec have led to the recent development and standardization of a lightweight image codec named JPEG XS. In this work we show that JPEG XS compression can be adapted to a specific given task and content, such as preserving visual quality on desktop content or maintaining high accuracy in neural network segmentation tasks, by optimizing its gain and priority parameters using the covariance matrix adaptation evolution strategy.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Brummer, B., & De Vleeschouwer, C. (2020). Adapting JPEG XS gains and priorities to tasks and contents. 3rd Workshop and Challenge on Learned Image Compression. Published. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle. https://hdl.handle.net/2078.5/219460