Picture Partitioning Design of Neural Network-Based Intra Coding For Video Coding For Machines
Keiichi Chono, Naoya Niwa, Hiroe Iwasaki · 2024
This paper presents a picture partitioning design of Neural Network-based Intra Coding (NNIC) for Video Coding for Machines (VCM). The proposed design introduces adaptive auto-encoder and probability model processing, and a new unit for the partitions of a NNIC picture. In conscious with the causality of the transmission order of the partitions, the adaptive auto-encoder processing exploits more the correlations of pixel values around the partition boundaries than a conventional design. Therefore it can bring coding gains while keeping low-delay video transmission capability. The adaptive probability model processing allows both encoder and decoder to start their entropy coding and decoding with the same delay as the conventional design. The new unit makes the picture partition signaling of NNIC compatible with that of Versatile Video Coding (VVC) forming the inner video coding of VCM. Simulation results show that, compared to the conventional, the proposal can attain the bit rate reduction of 11% on average with respect to machine tasks.