Deep Low-Contrast Image Enhancement using Structure Tensor Representation


  • Hyungjoo Jung Yonsei University Korea Institute of Science and Technology (KIST)
  • Hyunsung Jang Yonsei University LIG Nex1
  • Namkoo Ha LIG Nex1
  • Kwanghoon Sohn Yonsei University



Computational Photography, Image & Video Synthesis


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 tensor 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.




How to Cite

Jung, H., Jang, H., Ha, N., & Sohn, K. (2021). Deep Low-Contrast Image Enhancement using Structure Tensor Representation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1725-1733.



AAAI Technical Track on Computer Vision I