Neural Compression of 360-Degree Equirectangular Videos using Quality Parameter Adaptation

TL;DR

This paper introduces a method for improving neural video compression of 360-degree videos by adapting quality parameters based on latitude, achieving better compression efficiency without retraining models.

Contribution

It extends traditional quantization parameter adaptation techniques to neural video compression, enabling flexible quality control without additional training or architecture changes.

Findings

Achieves 5.2% BD-Rate savings in spherical PSNR.

Requires only 0.3% more processing time.

Effective for equirectangular 360-degree videos.

Abstract

This study proposes a practical approach for compressing 360-degree equirectangular videos using pretrained neural video compression (NVC) models. Without requiring additional training or changes in the model architectures, the proposed method extends quantization parameter adaptation techniques from traditional video codecs to NVC, utilizing the spatially varying sampling density in equirectangular projections. We introduce latitude-based adaptive quality parameters through rate-distortion optimization for NVC. The proposed method utilizes vector bank interpolation for latent modulation, enabling flexible adaptation with arbitrary quality parameters and mitigating the limitations caused by rounding errors in the adaptive quantization parameters. Experimental results demonstrate that applying this method to the DCVC-RT framework yields BD-Rate savings of 5.2% in terms of the weighted spherical peak signal-to-noise ratio for JVET class S1 test sequences, with only a 0.3% increase in processing time.