Controlling Neural Style Transfer with Deep Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters. In this paper, we propose the first deep Reinforcement Learning (RL) based architecture that splits one-step style transfer into a step-wise process for the NST task. Our RL-based method tends to preserve more details and structures of the content image in early steps, and synthesize more style patterns in later steps. It is a user-easily-controlled style-transfer method. Additionally, as our RL-based model performs the stylization progressively, it is lightweight and has lower computational complexity than existing one-step Deep Learning (DL) based models. Experimental results demonstrate the effectiveness and robustness of our method.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 30 Sep 2023.
Builds on
31 of 53 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 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
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
- 2018DeepMind Control Suitecited by 935
- 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
19 more
- 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
- 2015A Neural Algorithm of Artistic Stylecited by 480
- 2014Understanding Deep Image Representations by Inverting Themcited by 399
- 2017Universal Style Transfer via Feature Transformscited by 352
- 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
- 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
- 2016Learning to Navigate in Complex Environmentscited by 192
- 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
- 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
- 2017Demystifying Neural Style Transfercited by 152
- 2018Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decorationcited by 115
- 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
- 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
- 2020Arbitrary Video Style Transfer via Multi-Channel Correlationcited by 84
- 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
- 2021Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfercited by 41
- 2021Style-Aware Normalized Loss for Improving Arbitrary Style Transfercited by 30
- 2022RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Controlcited by 5
- 2021Stochastic Actor-Executor-Critic for Image-to-Image Translationcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.