论文标题
学习端到端图像压缩的真实速率优化 - 优化
Learning True Rate-Distortion-Optimization for End-To-End Image Compression
论文作者
论文摘要
即使速率优化是传统图像和视频压缩的关键部分，但并非存在将此概念转移到端到端训练的图像压缩的方法。大多数框架都包含在训练后固定的静态压缩和减压模型，因此不可能进行有效的速率延伸优化。在先前的工作中，我们提出了RDONET，它使RDO方法与HEVC中的自适应块分配相当。在本文中，我们通过将RDO结果的低复杂性估计引入培训来增强培训。此外，我们提出了快速，非常快速的RDO推理模式。通过我们的新型培训方法，我们在MS-SSIM中获得了平均节省的速率，而MS-SSIM比以前的RDONET模型达到了相当于的常规深层图像编码器的速率27.3％。
Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression and decompression models which are fixed after training, so efficient rate-distortion optimization is not possible. In a previous work, we proposed RDONet, which enables an RDO approach comparable to adaptive block partitioning in HEVC. In this paper, we enhance the training by introducing low-complexity estimations of the RDO result into the training. Additionally, we propose fast and very fast RDO inference modes. With our novel training method, we achieve average rate savings of 19.6% in MS-SSIM over the previous RDONet model, which equals rate savings of 27.3% over a comparable conventional deep image coder.
