Analyzing Time Complexity of Practical Learned Image Compression Models

We have witnessed the rapid development of learned image compression (LIC). The latest LIC models have outperformed almost all traditional image compression standards in terms of rate-distortion (RD) performance. However, the time complexity of LIC model is still underdiscovered, limiting the practical applications in industry. Even with the acceleration of GPU, LIC models still struggle with long coding time, especially on the decoder side. In this paper, we analyze and test a few prevailing and representative LIC models, and compare their complexity with traditional codecs including H.265/HEVC intra and H.266/VVC intra. We provide a comprehensive analysis on every module in the LIC models, and investigate how bitrate changes affect coding time. We observe that the time complexity bottleneck mainly exists in entropy coding and context modelling. Although this paper pay more attention to experimental statistics, our analysis reveals some insights for further acceleration of LIC model, such as model modification for parallel computing, model pruning and a more parallel context model.

I. Introduction

In recent years, learned image compression (LIC) models have achieved remarkable progresses. Researchers in this field have paid a lot of efforts to explore framework designing of LIC model, from recurrent networks [1]–[3], to variational autoencoders (VAE) [4]–[11] and incorporation of generative adversarial networks [12]–[14]. The current state-of-the-art LIC models have surpassed the H.266/VVC intra coding standard [15] in terms of both PSNR [16] and MS-SSIM [17].