Region-level bit allocation for rate control of 360-degree videos using cubemap projection

Abstract

Featuring with more uniform sampling density in the sphere domain and less non-uniform geometric deformations in the planar domain, variants of cubemap projection (CMP) format enable the higher compression ratio in on-going 360-degree video coding standardization. Different from single-view videos, 360-degree CMP videos feature with content discontinuity combined with the abrupt change of motion vectors between some adjacent faces. However, there is few bit allocation scheme designed for rate control of video coding of CMP format. Thus, this paper proposes a region-level bit allocation scheme for rate control of interframe coding of CMP format. The proposed scheme consists of two parts. The first part is machine learning based high HEVC coding cost region detection for individual faces, where the feature descriptor of a CTU consists of the face based texture complexity, motion magnitude, motion density, and temporal coherence of motion vector. The second part is fitting function based region-level bit allocation. Different from previous work, bits are assigned to the high coding cost region and non-high coding cost region in individual faces of CMP format. Experimental results indicate that the proposed scheme achieves higher bitrate accuracy and larger BD-WS-PSNR compared with the original rate control scheme of the reference software of HEVC, HM16.16 with the 360Lib.