The JPEG Committee has launched the learning-based image coding activity, also referred to as JPEG AI. This activity aims to find evidence for image coding technologies that offer substantially better compression efficiency than available image codecs with models obtained from a large amount of visual data and that can efficiently represent the wide variety of visual content that is available nowadays.

A Call for Evidence (CfE) has been issued as an outcome of the 86th JPEG meeting, Sydney, Australia as a first formal step to consider standardization of such approaches in image compression. The CfE is organized in coordination with the IEEE MMSP 2020 Challenge on Learning-based Image Coding and will use the same content, evaluation methodologies and deadlines.

The deadline for registration is May 30th, 2020. Submissions to the Call for Evidence are due 12th June, 2020 (decoder) and 18th June (code-streams and decoded images).

To stay informed on JPEG AI activities, please regularly consult our website at jpeg.org and/or subscribe to our e-mail reflector.