论文标题
使用优化分配的位分配
Bit Allocation using Optimization
论文作者
论文摘要
在本文中，我们考虑了神经视频压缩（NVC）中位分配的问题。首先，我们揭示了NVC中的位分配与半损坏的变异推理（SAVI）之间的基本关系。具体而言，我们表明具有GOP（图组）级别的SAVI相当于像素级位分配，并具有精确的速率\＆质量依赖性模型。基于这种等价性，我们使用SAVI建立了一个新的位分配范式。与以前的位分配方法不同，我们的方法不需要经验模型，因此是最佳的。此外，由于使用梯度上升的原始savi仅适用于单级潜在，因此我们通过递归通过梯度上升来递归施加后传播，将savi扩展到多层次（例如NVC）。最后，我们提出了一个可进行实施的典型近似值。我们的方法可以应用于性能超重编码速度的方案，并作为对位分配的R-D性能的经验约束。实验结果表明，与我们相比，当前最新的位分配算法仍然具有约0.5 $ db psnr的房间。代码可在\ url {https://github.com/tongdaxu/bit-allocation-aslocation-using-optimization}中获得。
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC). First, we reveal a fundamental relationship between bit allocation in NVC and Semi-Amortized Variational Inference (SAVI). Specifically, we show that SAVI with GoP (Group-of-Picture)-level likelihood is equivalent to pixel-level bit allocation with precise rate \& quality dependency model. Based on this equivalence, we establish a new paradigm of bit allocation using SAVI. Different from previous bit allocation methods, our approach requires no empirical model and is thus optimal. Moreover, as the original SAVI using gradient ascent only applies to single-level latent, we extend the SAVI to multi-level such as NVC by recursively applying back-propagating through gradient ascent. Finally, we propose a tractable approximation for practical implementation. Our method can be applied to scenarios where performance outweights encoding speed, and serves as an empirical bound on the R-D performance of bit allocation. Experimental results show that current state-of-the-art bit allocation algorithms still have a room of $\approx 0.5$ dB PSNR to improve compared with ours. Code is available at \url{https://github.com/tongdaxu/Bit-Allocation-Using-Optimization}.
