DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
This work addresses low-light image enhancement for computer vision applications, presenting an incremental improvement by incorporating frequency domain processing.
The paper tackles the challenge of restoring lost details in low-light images by introducing a frequency-based approach, achieving superior results on LOL and MIT-Adobe FiveK datasets with improved dark detection performance.
Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.