Invertible Image Decolorization

Rui Zhao, Tianshan Liu, Jun Xiao, Daniel P.K. Lun, Kin Man Lam

Research output: Journal article publicationJournal articleAcademic researchpeer-review

18 Citations (Scopus)


Invertible image decolorization is a useful color compression technique to reduce the cost in multimedia systems. Invertible decolorization aims to synthesize faithful grayscales from color images, which can be fully restored to the original color version. In this paper, we propose a novel color compression method to produce invertible grayscale images using invertible neural networks (INNs). Our key idea is to separate the color information from color images, and encode the color information into a set of Gaussian distributed latent variables via INNs. By this means, we force the color information lost in grayscale generation to be independent of the input color image. Therefore, the original color version can be efficiently recovered by randomly re-sampling a new set of Gaussian distributed variables, together with the synthetic grayscale, through the reverse mapping of INNs. To effectively learn the invertible grayscale, we introduce the wavelet transformation into a UNet-like INN architecture, and further present a quantization embedding to prevent the information omission in format conversion, which improves the generalizability of the framework in real-world scenarios. Extensive experiments on three widely used benchmarks demonstrate that the proposed method achieves a state-of-the-art performance in terms of both qualitative and quantitative results, which shows its superiority in multimedia communication and storage systems.

Original languageEnglish
Article number9467808
Pages (from-to)6081-6095
Number of pages15
JournalIEEE Transactions on Image Processing
Publication statusPublished - Jun 2021


  • color restoration
  • image decolorization
  • Invertible learning
  • invertible neural networks
  • wavelet decomposition

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Invertible Image Decolorization'. Together they form a unique fingerprint.

Cite this