Abstract:
This paper proposes a new neural network for enhancing underexposed images. Instead of the decomposition method based on Retinex theory, we introduce smooth dilated convo...Show MoreMetadata
Abstract:
This paper proposes a new neural network for enhancing underexposed images. Instead of the decomposition method based on Retinex theory, we introduce smooth dilated convolution to estimate global illumination of the input image, and implement an end-to-end learning network model. Based on this model, we formulate a multi-term loss function that combines content, color, texture and smoothness losses. Our extensive experiments demonstrate that this method is superior to other methods in underexposed image enhancement. It can cover more color details and be applied to various underexposed images robustly.
Published in: 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)
Date of Conference: 01-04 December 2020
Date Added to IEEE Xplore: 29 December 2020
ISBN Information: