This paper aims to delve into the rate-distortion-complexity trade-offs of modern neural video coding. Recent years have witnessed much research effort being focused on exploring the full potential of neural video cod...
详细信息
ISBN:
(纸本)9798350387261;9798350387254
This paper aims to delve into the rate-distortion-complexity trade-offs of modern neural video coding. Recent years have witnessed much research effort being focused on exploring the full potential of neural video coding. conditional autoencoders have emerged as the mainstream approach to efficient neural video coding. The central theme of conditional autoencoders is to leverage both spatial and temporal information for better conditionalcoding. However, a recent study indicates that conditionalcoding may suffer from information bottlenecks, potentially performing worse than traditional residualcoding. To address this issue, recent conditionalcoding methods incorporate a large number of high-resolution features as the condition signal, leading to a considerable increase in the number of multiply-accumulate operations, memory footprint, and model size. Taking DCVC as the common code base, we investigate how the newly proposed conditionalresidualcoding, an emerging new school of thought, and its variants may strike a better balance among rate, distortion, and complexity.
暂无评论