Image Restoration(Inpainting) using DCGAN (Apr '20)

  • Implemented based on the IEEE paper "Semantic Image Inpainting using Deep Generative Models
  • Auto generated incomplete patches in an image.
  • Designed a DCGAN network in python using tensorflow.
  • Trained and tested using CelebA_HQ dataset
  • Preprocessed and trained 10k images over the network for 8000 iterations using Cuda and CuDnn
  • Obtained a reduced loss when compared to other conventional image restoration techniques like auto encoders.

Phone

(919) 931-3183

Address