Q-LIC: Quantizing Learned Image Compression with Channel Splitting

Heming Sun, Lu Yu, Jiro Katto

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


Learned image compression (LIC) has reached a comparable coding gain with traditional hand-crafted methods such as VVC intra. However, the large network complexity prohibits the usage of LIC on resource-limited embedded systems. Network quantization is an efficient way to reduce the network burden. This paper presents a quantized LIC (QLIC) by channel splitting. First, we explore that the influence of quantization error to the reconstruction error is different for various channels. Second, we split the channels whose quantization has larger influence to the reconstruction error. After the splitting, the dynamic range of channels is reduced so that the quantization error can be reduced. Finally, we prune several channels to keep the number of overall channels as origin. By using the proposal, in the case of 8-bit quantization for weight and activation of both main and hyper path, we can reduce the BD-rate by 0.61%-4.74% compared with the previous QLIC. Besides, we can reach better coding gain compared with the state-of-the-art network quantization method when quantizing MS-SSIM models. Moreover, our proposal can be combined with other network quantization methods to further improve the coding gain. The moderate coding loss caused by the quantization validates the feasibility of the hardware implementation for QLIC in the future.

Original languageEnglish
Pages (from-to)1
Number of pages1
JournalIEEE Transactions on Circuits and Systems for Video Technology
Publication statusAccepted/In press - 2022


  • Arithmetic
  • Hardware
  • Image coding
  • Image reconstruction
  • Learned image compression
  • Mathematical models
  • Quantization (signal)
  • Transforms
  • channel splitting
  • fixed-point
  • quantization

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering


Dive into the research topics of 'Q-LIC: Quantizing Learned Image Compression with Channel Splitting'. Together they form a unique fingerprint.

Cite this