Jung, Hyungjoo Sohn, Kwanghoon Ha, Namkoo Jang, Hyunsung 2024-01-19T09:08:38Z 2024-01-19T09:08:38Z 2022-02-26 2021-02 2159-5399 https://pubs.kist.re.kr/handle/201004/113578 We present a new deep learning framework for low-contrast image enhancement, which trains the network using the multi-exposure sequences rather than explicit ground-truth images. The purpose of our method is to enhance a low-contrast image so as to contain abundant details in various exposure levels. To realize this, we propose to design the loss function using the structure tensor representation, which has been widely used as high-dimensional image contrast. Our loss function penalizes the difference of the structure tensors between the network output and the multi-exposure images in a multi-scale manner. Eventually, the network trained by the loss function produces a high-quality image approximating the overall contrast of the sequence. We provide in-depth analysis on our method and comparison with conventional loss functions. Quantitative and qualitative evaluations demonstrate that the proposed method outperforms the existing state-of-the art approaches in various benchmarks. English ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE Deep Low-Contrast Image Enhancement using Structure Tensor Representation Conference 1 35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence, pp.1725 - 1733 35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence 1725 1733 US ELECTR NETWORK 2021-02-02 THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE 000680423501091