TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Single Low-Light Ghost-Free Image Enhancement via Deep Retinex Model |
¿µ¹®Á¦¸ñ(English Title) |
Single Low-Light Ghost-Free Image Enhancement via Deep Retinex Model |
ÀúÀÚ(Author) |
Chunmao Wu
Huayuan Xu
Ziyang Liu
Yan Liu
Bingxue Lv
Jingwen Wang
Wei Huang
Tiantian Qiu
Yunzhong Chen
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 15 NO. 05 PP. 1814 ~ 1828 (2021. 05) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from lowresolution. To reduce the noise of the enhanced image and improve the image quality, a superresolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.
|
Å°¿öµå(Keyword) |
Positive Experience
IoT Product
Artificial Intelligent
Design Approach.
image enhancement
low-light image
Retinex model
image decomposition
super-resolution
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|