Guo Jinyang, Xu Dong, Lu Guo
IEEE Trans Image Process. 2023;32:2049-2062. doi: 10.1109/TIP.2023.3251020.
In this work, we propose a new deep image compression framework called Complexity and Bitrate Adaptive Network (CBANet) that aims to learn one single network to support variable bitrate coding under various computational complexity levels. In contrast to the existing state-of-the-art learning-based image compression frameworks that only consider the rate-distortion trade-off without introducing any constraint related to the computational complexity, our CBANet considers the complex rate-distortion-complexity trade-off when learning a single network to support multiple computational complexity levels and variable bitrates. Since it is a non-trivial task to solve such a rate-distortion-complexity related optimization problem, we propose a two-step approach to decouple this complex optimization task into a complexity-distortion optimization sub-task and a rate-distortion optimization sub-task, and additionally propose a new network design strategy by introducing a Complexity Adaptive Module (CAM) and a Bitrate Adaptive Module (BAM) to respectively achieve the complexity-distortion and rate-distortion trade-offs. As a general approach, our network design strategy can be readily incorporated into different deep image compression methods to achieve complexity and bitrate adaptive image compression by using a single network. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of our CBANet for deep image compression. Code is released at https://github.com/JinyangGuo/CBANet-release.
在这项工作中，我们提出了一种名为复杂度与比特率自适应网络（CBANet）的新型深度图像压缩框架，其旨在学习一个单一网络，以在各种计算复杂度级别下支持可变比特率编码。与现有的仅考虑率失真权衡而不引入任何与计算复杂度相关约束的基于学习的图像压缩框架不同，我们的CBANet在学习单个网络以支持多个计算复杂度级别和可变比特率时考虑了复杂的率失真 - 复杂度权衡。由于解决这样一个与率失真 - 复杂度相关的优化问题并非易事，我们提出了一种两步法，将这个复杂的优化任务解耦为一个复杂度 - 失真优化子任务和一个率失真优化子任务，并且另外提出了一种新的网络设计策略，通过引入一个复杂度自适应模块（CAM）和一个比特率自适应模块（BAM）来分别实现复杂度 - 失真和率失真权衡。作为一种通用方法，我们的网络设计策略可以很容易地融入不同的深度图像压缩方法中，以通过使用单个网络实现复杂度和比特率自适应图像压缩。在两个基准数据集上进行的综合实验证明了我们的CBANet在深度图像压缩方面的有效性。代码已在https://github.com/JinyangGuo/CBANet-release上发布。
