S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention (2210.12381v3)
Abstract: Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling. This paper introduces Strips Window Attention Transformer (S2WAT), a novel hierarchical vision transformer designed for style transfer. S2WAT employs attention computation in diverse window shapes to capture both short- and long-range dependencies. The merged dependencies utilize the "Attn Merge" strategy, which adaptively determines spatial weights based on their relevance to the target. Extensive experiments on representative datasets show the proposed method's effectiveness compared to state-of-the-art (SOTA) transformer-based and other approaches. The code and pre-trained models are available at https://github.com/AlienZhang1996/S2WAT.
- Artflow: Unbiased image style transfer via reversible neural flows. In CVPR.
- ITstyler: Image-optimized Text-based Style Transfer. arXiv.
- Longformer: The long-document transformer. arXiv.
- The image local autoregressive transformer. Advances in Neural Information Processing Systems, 34: 18433–18445.
- Stylebank: An explicit representation for neural image style transfer. In CVPR.
- Artistic style transfer with internal-external learning and contrastive learning. In NeurIPS.
- Long short-term memory-networks for machine reading. In EMNLP.
- Arbitrary video style transfer via multi-channel correlation. In AAAI.
- StyTr2: Image Style Transfer with Transformers. In CVPR.
- Arbitrary style transfer via multi-adaptation network. In ACM MM.
- Cswin transformer: A general vision transformer backbone with cross-shaped windows. In CVPR.
- Image quilting for texture synthesis and transfer. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques.
- Multiscale vision transformers. In ICCV.
- Texture synthesis using convolutional neural networks. In NeurIPS.
- A neural algorithm of artistic style. In Vision Sciences Society.
- Levit: a vision transformer in convnet’s clothing for faster inference. In ICCV.
- AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks. In ICCV.
- Arbitrary style transfer in real-time with adaptive instance normalization. In ICCV.
- Perceptual losses for real-time style transfer and super-resolution. In ECCV.
- Adam: A method for stochastic optimization. In ICLR.
- Exploring the Temporal Consistency of Arbitrary Style Transfer: A Channelwise Perspective. IEEE Transactions on Neural Networks and Learning Systems.
- Arbitrary Style Transfer with Semantic Content Enhancement. In The 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry.
- Universal style transfer via feature transforms. In NeurIPS.
- Microsoft coco: Common objects in context. In ECCV.
- Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV.
- Name your style: An arbitrary artist-aware image style transfer. arXiv.
- RAST: Restorable Arbitrary Style Transfer via Multi-Restoration. In WACV.
- Arbitrary style transfer with style-attentional networks. In CVPR.
- Automatic differentiation in pytorch. In NeurIPS.
- Wiki Art Gallery, Inc.: A case for critical thinking. Issues in Accounting Education.
- Instance normalization: The missing ingredient for fast stylization. arXiv.
- Attention is all you need. In NeurIPS.
- Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In ICCV.
- Cvt: Introducing convolutions to vision transformers. In ICCV.
- Styleformer: Real-time arbitrary style transfer via parametric style composition. In ICCV.
- SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34: 12077–12090.
- On layer normalization in the transformer architecture. In ICML.
- Attention-aware multi-stroke style transfer. In CVPR.
- Inversion-based style transfer with diffusion models. In CVPR, 10146–10156.
- Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning. In SIGGRAPH.
- All-to-key Attention for Arbitrary Style Transfer. In ICCV.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.