PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 1, 2018195 citations

Arbitrary Style Transfer with Deep Feature Reshuffle

View Full Paper
SGShuyang GuCCCongliang ChenJLJing Liao

Key Points

Key points are not available for this paper at this time.

Abstract

This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theoretically prove that our new style loss based on reshuffle connects both global and local style losses respectively used by most parametric and non-parametric neural style transfer methods. This simple idea can effectively address the challenging issues in existing style transfer methods. On one hand, it can avoid distortions in local style patterns, and allow semantic-level transfer, compared with neural parametric methods. On the other hand, it can preserve globally similar appearance to the style image, and avoid wash-out artifacts, compared with neural non-parametric methods. Based on the proposed loss, we also present a progressive feature-domain optimization approach. The experiments show that our method is widely applicable to various styles, and produces better quality than existing methods.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Gu et al. (2018) studied this question.

synapsesocial.com/papers/6a1034c85725bbd5cc60a770https://doi.org/10.1109/cvpr.2018.00858
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Controlling Perceptual Factors in Neural Style Transfer2017 · 519 citations
  2. 2Decoder Network over Lightweight Reconstructed Feature for Fast Semantic Style Transfer2017 · 57 citations
  3. 3Neural Style Transfer: A Review2017 · 103 citations
  4. 4Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017 · 5,038 citations
  5. 5Fast Patch-based Style Transfer of Arbitrary Style2016 · 222 citations