JPEG AI - Learning-based Image Coding Common Test Conditions
This document defines the common test conditions (CTC) that should be used to evaluate the different aspects of learning-based image codecs, i.e. for any JPEG AI image coding experiments. Moreover, the JPEG AI CTC are recommended for use in any JPEG AI technical contributions to the 90th and following JPEG meetings. The CTC document defines the datasets, anchors, target bitrates, and objective and subjective quality evaluation procedures.
To stay informed on JPEG AI activities, please regularly consult our website at jpeg.org and/or subscribe to our e-mail reflector.