TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer
Not on the map. Why?
Abstract (arXiv)
Artistic style transfer aims to create new artistic images by rendering a given photograph with the target artistic style. Existing methods learn styles simply based on global statistics or local patches, lacking careful consideration of the drawing process in practice. Consequently, the stylization results either fail to capture abundant and diversified local style patterns, or contain undesired semantic information of the style image and deviate from the global style distribution. To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects. Moreover, to further enhance both content and style representations, we introduce two novel losses: an attention-based content loss and a patch-based style loss, where the former enables better content preservation by enforcing the semantic relation in the content image to be retained during stylization, and the latter focuses on increasing the local style similarity between the style and stylized images. Extensive qualitative and quantitative experiments verify the effectiveness of our method.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 42 of its 57 references that are in the map. First posted on arXiv 12 Sep 2023.
Builds on
42 of 57 references.
References · 42
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2017Universal Style Transfer via Feature Transformscited by 352
- 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 258
- 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
30 more
- 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
- 2021StyTr2: Image Style Transfer with Transformerscited by 186
- 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
- 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
- 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
- 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
- 2018Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decorationcited by 115
- 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
- 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
- 2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
- 2016Fast Patch-based Style Transfer of Arbitrary Stylecited by 92
- 2019Dynamic Instance Normalization for Arbitrary Style Transfercited by 83
- 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
- 2013Recognizing Image Stylecited by 64
- 2018A Style-Aware Content Loss for Real-time HD Style Transfercited by 58
- 2019Attention-aware Multi-stroke Style Transfercited by 47
- 2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
- 2019Diversified Arbitrary Style Transfer via Deep Feature Perturbationcited by 42
- 2021Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfercited by 41
- 2021DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfercited by 38
- 2021Language-Driven Image Style Transfercited by 36
- 2020Manifold Alignment for Semantically Aligned Style Transfercited by 34
- 2019Multimodal Style Transfer via Graph Cutscited by 32
- 2021In the light of feature distributions: moment matching for Neural Style Transfercited by 26
- 2022AesUST: Towards Aesthetic-Enhanced Universal Style Transfercited by 21
- 2020A Content Transformation Block For Image Style Transfercited by 19
- 2022MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfercited by 19
- 2018EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfercited by 13
- 2021DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfercited by 11
- 2022Industrial Style Transfer with Large-scale Geometric Warping and Content Preservationcited by 9
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.