Perceptual Losses for Real-Time Style Transfer and Super-Resolution

  title={Perceptual Losses for Real-Time Style Transfer and Super-Resolution},
  author={Justin Johnson and Alexandre Alahi and Li Fei-Fei},
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing perceptual loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose… CONTINUE READING
Highly Influential
This paper has highly influenced 126 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 1,120 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 224 times over the past 90 days. VIEW TWEETS
Blog posts, news articles and tweet counts and IDs sourced by