Back to Search Document details
28th Meeting: Mainz, DE, October 2022 2022-10-20 22:37
Crosscheck of JVET-AB0068 (EE1-1.6: RDO Considering Deep In-Loop Filtering)
Abstract
This contribution reports on a training and inference crosscheck of EE1-1.6, proposed at the last meeting as JVET-AA0113 and presented at this meeting in JVET-AB0068. Two networks, luma-intra-RDO and luma-inter-RDO, were trained from scratch using training data extracted using the supplied software. The networks were converted to integer SADL and then evaluated against NNVC-2.0 and NCS 1.0 filter set 1. In the evaluation, the models used for actual NN loop filtering were the same as the one in JVET-AA0113, only the luma-intra-RDO and luma-inter-RDO were changed to the retrained versions. The results using the retrained version compared to JVET-AB0068 are reported to be:
References:
Citation