TY - JOUR AU - Pan, Jinshan AU - Liu, Yang AU - Sun, Deqing AU - Ren, Jimmy AU - Cheng, Ming-Ming AU - Yang, Jian AU - Tang, Jinhui PY - 2020/04/03 Y2 - 2024/03/28 TI - Image Formation Model Guided Deep Image Super-Resolution JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 34 IS - 07 SE - AAAI Technical Track: Vision DO - 10.1609/aaai.v34i07.6853 UR - https://ojs.aaai.org/index.php/AAAI/article/view/6853 SP - 11807-11814 AB - <p>We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution. The proposed algorithm first uses a deep neural network to estimate intermediate high-resolution images, blurs the intermediate images using known blur kernels, and then substitutes values of the pixels at the un-decimated positions with those of the corresponding pixels from the low-resolution images. The output of the pixel substitution process strictly satisfies the image formation model and is further refined by the same deep neural network in a cascaded manner. The proposed framework is trained in an end-to-end fashion and can work with existing feed-forward deep neural networks for super-resolution and converges fast in practice. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.</p> ER -