Adaptive Rate Control for Deep Video Compression with Rate-Distortion Prediction
This work addresses the problem of efficient and accurate rate control for deep video compression, which is incremental as it adapts existing neural methods to a specific bottleneck in video coding.
The paper tackles the lack of tailored rate control schemes in deep video compression by proposing a neural network-based method that predicts rate-distortion relationships from uncompressed frames to determine coding parameters, achieving high accuracy with low time overhead and reducing quality fluctuations across resolutions.
Deep video compression has made significant progress in recent years, achieving rate-distortion performance that surpasses that of traditional video compression methods. However, rate control schemes tailored for deep video compression have not been well studied. In this paper, we propose a neural network-based $λ$-domain rate control scheme for deep video compression, which determines the coding parameter $λ$ for each to-be-coded frame based on the rate-distortion-$λ$ (R-D-$λ$) relationships directly learned from uncompressed frames, achieving high rate control accuracy efficiently without the need for pre-encoding. Moreover, this content-aware scheme is able to mitigate inter-frame quality fluctuations and adapt to abrupt changes in video content. Specifically, we introduce two neural network-based predictors to estimate the relationship between bitrate and $λ$, as well as the relationship between distortion and $λ$ for each frame. Then we determine the coding parameter $λ$ for each frame to achieve the target bitrate. Experimental results demonstrate that our approach achieves high rate control accuracy at the mini-GOP level with low time overhead and mitigates inter-frame quality fluctuations across video content of varying resolutions.