Fig 4 - uploaded by Chi-Mao Fan
Content may be subject to copyright.
Visual comparisons for low-light image enhancement on the MIT-Adobe FiveK dataset [26].

Visual comparisons for low-light image enhancement on the MIT-Adobe FiveK dataset [26].

Source publication
Preprint
Full-text available
Low-Light Image Enhancement is a computer vision task which intensifies the dark images to appropriate brightness. It can also be seen as an ill-posed problem in image restoration domain. With the success of deep neural networks, the convolutional neural networks surpass the traditional algorithm-based methods and become the mainstream in the compu...

Contexts in source publication

Context 1
... the computational complexity [17], and the design of wavelet attention could gain more semantic information and details in the training process to keep satisfactory results. Evaluation on MIT-Adobe FiveK. As for the MIT-5K [26], the average performance scores on the testing set and comparisons of some enhanced image are shown in Table 2 and Fig. 4. It shows that the proposed HWMNet still achieves state-of-the-art performance on both PSNR and ...
Context 2
... the computational complexity [17], and the design of wavelet attention could gain more semantic information and details in the training process to keep satisfactory results. Evaluation on MIT-Adobe FiveK. As for the MIT-5K [26], the average performance scores on the testing set and comparisons of some enhanced image are shown in Table 2 and Fig. 4. It shows that the proposed HWMNet still achieves state-of-the-art performance on both PSNR and ...