Deep Spatial Adaptive Network for Real Image Demosaicing


  • Tao Zhang Beijing Institute of Technology
  • Ying Fu Beijing Institute of Technology
  • Cheng Li Huawei Noah's Ark Lab



Computer Vision (CV)


Demosaicing is the crucial step in the image processing pipeline and is a highly ill-posed inverse problem. Recently, various deep learning based demosaicing methods have achieved promising performance, but they often design the same nonlinear mapping function for different spatial location and are not well consider the difference of mosaic pattern for each color. In this paper, we propose a deep spatial adaptive network (SANet) for real image demosaicing, which can adaptively learn the nonlinear mapping function for different locations. The weights of spatial adaptive convolution layer are generated by the pattern information in the receptive filed. Besides, we collect a paired real demosaicing dataset to train and evaluate the deep network, which can make the learned demosaicing network more practical in the real world. The experimental results show that our SANet outperforms the state-of-the-art methods under both comprehensive quantitative metrics and perceptive quality in both noiseless and noisy cases.




How to Cite

Zhang, T., Fu, Y., & Li, C. (2022). Deep Spatial Adaptive Network for Real Image Demosaicing. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 3326-3334.



AAAI Technical Track on Computer Vision III