Multi-scale Progressive Feature Embedding for Accurate NIR-to-RGB Spectral Domain Translation

Xingxing Yang, Jie Chen*, Zaifeng Yang

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

NIR-to-RGB spectral domain translation is a challenging task due to the mapping ambiguities and existing methods show limited learning capacities. To address these challenges, we propose to colorize NIR images via a multi-scale progressive feature embedding network (MPFNet), with the guidance of grayscale image colorization. Specifically, we first introduce a domain translation module that translates NIR source images into the grayscale target domain. By incorporating a progressive training strategy, the statistical and semantic knowledge from both task domains are efficiently aligned with a series of pixel-/feature-level consistency constraints. Besides, a multi-scale progressive feature embedding network is designed to improve learning capabilities. Experiments show that our MPFNet outperforms state-of-the-art counterparts by 2.55dB in the NIR-to-RGB spectral domain translation task in terms of PSNR.
Original languageEnglish
Title of host publication2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)
PublisherIEEE
Number of pages5
ISBN (Electronic)9798350359855
ISBN (Print)9798350359862
DOIs
Publication statusPublished - Dec 2023
Event2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023 - Jeju, Korea, Republic of
Duration: 4 Dec 20237 Dec 2023
https://ieeexplore.ieee.org/xpl/conhome/10402600/proceeding

Publication series

NameIEEE Visual Communications and Image Processing (VCIP)
PublisherIEEE
ISSN (Print)1018-8770
ISSN (Electronic)2642-9357

Conference

Conference2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023
Country/TerritoryKorea, Republic of
CityJeju
Period4/12/237/12/23
Internet address

User-Defined Keywords

  • Near-Infrared image colorization
  • domain adaptation
  • Generative Adversarial Network
  • attention mechanism

Fingerprint

Dive into the research topics of 'Multi-scale Progressive Feature Embedding for Accurate NIR-to-RGB Spectral Domain Translation'. Together they form a unique fingerprint.

Cite this