mlsanityData to 7 Oct 2026

CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

arXiv 2303.17867 ↗First posted 31 Mar 2023cs.CV cs.LG eess.IVcited by 24

Not on the map. Why?

Abstract (arXiv)

Content affinity loss including feature and pixel affinity is a main problem which leads to artifacts in photorealistic and video style transfer. This paper proposes a new framework named CAP-VSTNet, which consists of a new reversible residual network and an unbiased linear transform module, for versatile style transfer. This reversible residual network can not only preserve content affinity but not introduce redundant information as traditional reversible networks, and hence facilitate better stylization. Empowered by Matting Laplacian training loss which can address the pixel affinity loss problem led by the linear transform, the proposed framework is applicable and effective on versatile style transfer. Extensive experiments show that CAP-VSTNet can produce better qualitative and quantitative results in comparison with the state-of-the-art methods.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 31 Mar 2023.

Builds on

30 of 41 references.

References · 30

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  8. 2020Reformer: The Efficient Transformercited by 1,658
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  10. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  11. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  12. 2018Invertible Residual Networkscited by 364
18 more
  1. 2017Universal Style Transfer via Feature Transformscited by 352
  2. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 215
  3. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
  4. 2017Deep Photo Style Transfercited by 168
  5. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  6. 2018i-RevNet: Deep Invertible Networkscited by 137
  7. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  8. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  9. 2015Optimal whitening and decorrelationcited by 93
  10. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  11. 2013Recognizing Image Stylecited by 64
  12. 2020Collaborative Distillation for Ultra-Resolution Universal Style Transfercited by 52
  13. 2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
  14. 2021Domain-Aware Universal Style Transfercited by 40
  15. 2019Ultrafast Photorealistic Style Transfer via Neural Architecture Searchcited by 39
  16. 2017Characterizing and Improving Stability in Neural Style Transfercited by 31
  17. 2016Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfercited by 30
  18. 2022PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 6; 2025: 9; 2026: 4.

24 papers.

Sort:

By area:

  1. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priorscited by 40
  2. 2023InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Advisercited by 17
  3. 2025Video Color Grading via Look-Up Table Generationcited by 9
  4. 2023Advances in 3D Neural Stylization: A Surveycited by 8
  5. 2024NADER: Neural Architecture Design via Multi-Agent Collaborationcited by 8
  6. 2025Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restorationcited by 8
  7. 2024Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Networkcited by 5
  8. 2024DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfercited by 5
  9. 2025SaMam: Style-aware State Space Model for Arbitrary Image Style Transfercited by 5
  10. 2025SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfercited by 4
  11. 20244DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splattingcited by 3
  12. 2025Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridgingcited by 2
12 more
  1. 2025Neural Scene Designer: Self-Styled Semantic Image Manipulationcited by 2
  2. 2025Personalized Image Filter: Mastering Your Photographic Stylecited by 2
  3. 2023Color and Texture Dual Pipeline Lightweight Style Transfercited by 1
  4. 2025RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generationcited by 1
  5. 2026CanonCGT: Reference-Based Color Grading via Canonical Pivot Representationcited by 1
  6. 2023RL-I2IT: Image-to-Image Translation with Deep Reinforcement Learningcited by 0
  7. 2024StyleBrush: Style Extraction and Transfer from a Single Imagecited by 0
  8. 2024MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Referencecited by 0
  9. 2025Pluggable Style Representation Learning for Multi-Style Transfercited by 0
  10. 2026SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learningcited by 0
  11. 2026Towards In-Context Tone Style Transfer with A Large-Scale Triplet Datasetcited by 0
  12. 2026ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matchingcited by 0