Structure-Texture Image Decomposition Using Deep Variational Priors

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Structure-Texture Image Decomposition Using Deep Variational Priors

Youngjung Kim; Bumsub Ham; Minh N. Do; Kwanghoon Sohn

Most variational formulations for structure-texture image decomposition force the structure images to have small norm in some functional spaces and to share a common notion of edges, i.e., large-gradients or large-intensity differences. However, such a definition makes it difficult to distinguish structure edges from oscillations that have fine spatial scale but high contrast. In this paper, we introduce a new model by learning deep variational priors for structure images without explicit training data. An alternating direction method of a multiplier algorithm and its modular structure are adopted to plug deep variational priors into an iterative smoothing process. The central observations are that convolution neural networks (CNNs) can replace the total variation prior, and are indeed powerful to capture the natures of structure and texture. We show that our learned priors using CNNs successfully differentiate high-amplitude details from structure edges, and avoid halo artifacts. Different from previous data-driven smoothing schemes, our formulation provides another degree of freedom to produce continuous smoothing effects. Experimental results demonstrate the effectiveness of our approach on various computational photography and image processing applications, including texture removal, detail manipulation, HDR tone-mapping, and non-photorealistic abstraction.

SPS on Twitter

  • The virtual conference is powered by leading companies who have continued to show their support for our t…
  • The virtual conference begins today! Join us all week long for an exciting week of inspiring, innovative…
  • Learn what's new with Society activities during the SPS Town Hall! Join SPS President Ahmed Tewfik on Wednesday, 28…
  • DEADLINE EXTENDED: The application deadline for PROGRESS at has been extended to Tuesday, 20 October. Det…
  • On Wednesday, 28 October, join Stefania Sardellitti for a new SPS Webinar, “Joint Optimization of Radio and Computa…

SPS Videos

Signal Processing in Home Assistants


Multimedia Forensics

Careers in Signal Processing             


Under the Radar