Multi-scale Progressive Feature Embedding for Accurate NIR-to-RGB Spectral Domain Translation
This work addresses a domain-specific problem in computer vision for applications like remote sensing or low-light imaging, with incremental improvements over existing methods.
The paper tackles the challenging problem of translating near-infrared (NIR) images to RGB images, which suffers from mapping ambiguities, by proposing a multi-scale progressive feature embedding network (MPFNet) that outperforms state-of-the-art methods by 2.55 dB in PSNR.
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- and 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 2.55 dB in the NIR-to-RGB spectral domain translation task in terms of PSNR.