0%

(CVPR 2018) Deep Image Prior

Ulyanov D, Vedaldi A, Lempitsky V. Deep image prior[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 9446-9454.



1. Overview


目前深度学习都是learning-based方式,论文将深度学习作为learning-free方式

  • used as handcrafted priors to solve inverse problems, such as denoising, super-resolution, inpainting, restore image based on flash-no flash image
  • generator network is sufficient to capture low-level image statistics proir
  • bridge the gap between learning-based and laerning-free
  • first study to investigates the prior captured by deep convolutional generative networks independently of learning the network parameters from images

1.1. Loss Function



  • input. random noise, usually initialize randomly and keep it fixed
  • gt. noise image

1.2. Converge

  • 图像的收敛比噪声快


1.3. 应用

  • Denoising




  • Super-Resolution



  1. input. random noise
  2. gt. H x W
  3. output. tH x tW, and then downsampled H x W


  • Inpainting


  1. output. x
  2. gt. x0, image with missing pixel
  3. m. binary mask



skip-connection对该类任务的效果较差



  • Natural Pre-image

pre-image



loss function




  • Flash-no Flash Reconstruction