7:00 – 5:00 ASRC GEOS

• Something else for image repair: Deep Image Prior
  • Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, and inpainting. Furthermore, the same prior can be used to invert deep neural representations to diagnose them, and to restore images based on flash-no flash input pairs.
• Dissertation/TAAS
• GEOS Sim
  • Building RCS controllers!
  • Record data
  • Spark lines
  • Excel outputs
  • Start physics