Adapting JPEG XS gains and priorities to tasks and contents
This work addresses the need for low-complexity image codecs in workflows with computing constraints, offering a domain-specific adaptation method for JPEG XS.
The paper tackled the problem of adapting JPEG XS compression to specific tasks and content, such as preserving visual quality or maintaining segmentation accuracy, by optimizing its parameters using the covariance matrix adaptation evolution strategy, resulting in tailored compression without specifying concrete numbers.
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.