File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Towards ultra-resolution neural style transfer via thumbnail instance normalization
Title | Towards ultra-resolution neural style transfer via thumbnail instance normalization |
---|---|
Authors | |
Keywords | Computer vision (CV) |
Issue Date | 2022 |
Publisher | Association for the Advancement of Artificial Intelligence. |
Citation | 36th AAAI Conference on Artificial Intelligence (Virtual), February 22-March 1, 2022. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), v. 36, p. 393-400 How to Cite? |
Abstract | We present an extremely simple Ultra-Resolution Style Transfer framework, termed URST, to flexibly process arbitrary high-resolution images (e.g., 10000x10000 pixels) style transfer for the first time. Most of the existing state-of-the-art methods would fall short due to massive memory cost and small stroke size when processing ultra-high resolution images. URST completely avoids the memory problem caused by ultra-high resolution images by (1) dividing the image into small patches and (2) performing patch-wise style transfer with a novel Thumbnail Instance Normalization (TIN). Specifically, TIN can extract thumbnail features' normalization statistics and apply them to small patches, ensuring the style consistency among different patches. Overall, the URST framework has three merits compared to prior arts. (1) We divide input image into small patches and adopt TIN, successfully transferring image style with arbitrary high-resolution. (2) Experiments show that our URST surpasses existing SOTA methods on ultra-high resolution images benefiting from the effectiveness of the proposed stroke perceptual loss in enlarging the stroke size. (3) Our URST can be easily plugged into most existing style transfer methods and directly improve their performance even without training. |
Description | AAAI-22 Technical Tracks 1 |
Persistent Identifier | http://hdl.handle.net/10722/315793 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, Z | - |
dc.contributor.author | Wang, W | - |
dc.contributor.author | Xie, E | - |
dc.contributor.author | Luo, P | - |
dc.date.accessioned | 2022-08-19T09:04:32Z | - |
dc.date.available | 2022-08-19T09:04:32Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | 36th AAAI Conference on Artificial Intelligence (Virtual), February 22-March 1, 2022. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), v. 36, p. 393-400 | - |
dc.identifier.uri | http://hdl.handle.net/10722/315793 | - |
dc.description | AAAI-22 Technical Tracks 1 | - |
dc.description.abstract | We present an extremely simple Ultra-Resolution Style Transfer framework, termed URST, to flexibly process arbitrary high-resolution images (e.g., 10000x10000 pixels) style transfer for the first time. Most of the existing state-of-the-art methods would fall short due to massive memory cost and small stroke size when processing ultra-high resolution images. URST completely avoids the memory problem caused by ultra-high resolution images by (1) dividing the image into small patches and (2) performing patch-wise style transfer with a novel Thumbnail Instance Normalization (TIN). Specifically, TIN can extract thumbnail features' normalization statistics and apply them to small patches, ensuring the style consistency among different patches. Overall, the URST framework has three merits compared to prior arts. (1) We divide input image into small patches and adopt TIN, successfully transferring image style with arbitrary high-resolution. (2) Experiments show that our URST surpasses existing SOTA methods on ultra-high resolution images benefiting from the effectiveness of the proposed stroke perceptual loss in enlarging the stroke size. (3) Our URST can be easily plugged into most existing style transfer methods and directly improve their performance even without training. | - |
dc.language | eng | - |
dc.publisher | Association for the Advancement of Artificial Intelligence. | - |
dc.relation.ispartof | Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) | - |
dc.subject | Computer vision (CV) | - |
dc.title | Towards ultra-resolution neural style transfer via thumbnail instance normalization | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.doi | 10.1609/aaai.v36i1.19916 | - |
dc.identifier.hkuros | 335564 | - |
dc.identifier.volume | 36 | - |
dc.identifier.spage | 393 | - |
dc.identifier.epage | 400 | - |
dc.publisher.place | United States | - |