论文标题
最佳控制感知损耗压缩
Optimally Controllable Perceptual Lossy Compression
论文作者
论文摘要
最近对压缩的最新研究表明，失真和感知质量彼此不一致，这会导致失真和感知之间的权衡（D-P）。直观地，要获得不同的感知质量，必须培训不同的解码器。在本文中，我们提出了一个非平凡的发现，即只有两个解码器足以实现任意（无限数量的不同）D-P取舍。我们证明，通过最小MSE解码器的输出和专门构造的完美感知解码器之间的简单线性插值可以实现D-P权衡约束的任意点。同时，可以通过插值因子定量控制感知质量（就平方的Wasserstein-2距离度量而言）。此外，为了构建一个完美的感知解码器，我们提出了两个理论上最佳的培训框架。新框架与基于扭曲 - 对抗损失的启发式框架不同，该框架广泛用于现有方法，这些框架不仅在理论上是最佳的，而且可以在实践感知解码中产生最先进的性能。最后，我们验证了我们的理论发现，并通过实验证明了框架的优越性。代码可在以下网址找到：https：//github.com/zeyuyan/controllable-coccepcepuly-compression
Recent studies in lossy compression show that distortion and perceptual quality are at odds with each other, which put forward the tradeoff between distortion and perception (D-P). Intuitively, to attain different perceptual quality, different decoders have to be trained. In this paper, we present a nontrivial finding that only two decoders are sufficient for optimally achieving arbitrary (an infinite number of different) D-P tradeoff. We prove that arbitrary points of the D-P tradeoff bound can be achieved by a simple linear interpolation between the outputs of a minimum MSE decoder and a specifically constructed perfect perceptual decoder. Meanwhile, the perceptual quality (in terms of the squared Wasserstein-2 distance metric) can be quantitatively controlled by the interpolation factor. Furthermore, to construct a perfect perceptual decoder, we propose two theoretically optimal training frameworks. The new frameworks are different from the distortion-plus-adversarial loss based heuristic framework widely used in existing methods, which are not only theoretically optimal but also can yield state-of-the-art performance in practical perceptual decoding. Finally, we validate our theoretical finding and demonstrate the superiority of our frameworks via experiments. Code is available at: https://github.com/ZeyuYan/Controllable-Perceptual-Compression
