Li, Jinmin;
Dai, Tao;
Zhang, Jingyun;
Liu, Kang;
Wang, Jun;
Wang, Shaoming;
Xia, Shu-Tao;
(2024)
Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling.
In: Larson, Kate, (ed.)
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24).
(pp. pp. 992-1000).
IJCAI: Jeju, Korea.
Preview |
Text
2405.02941v2.pdf - Accepted Version Download (5MB) | Preview |
Abstract
Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details, which thus hinders their real applications. To address this issue, we propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results. Unlike previous methods that model high-frequency information as standard Gaussian distribution directly, our BDFlow first decouples the high-frequency information into semantic high-frequency that adheres to a Boundary distribution and non-semantic high-frequency counterpart that adheres to a Gaussian distribution. Specifically, to capture semantic high-frequency parts accurately, we use Boundary-aware Mask (BAM) to constrain the model to produce rich textures, while non-semantic high-frequency part is randomly sampled from a Gaussian distribution. Comprehensive experiments demonstrate that our BDFlow significantly outperforms other state-of-the-art methods while maintaining lower complexity. Notably, our BDFlow improves the PSNR by 4.4 dB and the SSIM by 0.1 on average over GRAIN, utilizing only 74% of the parameters and 20% of the computation. The code will be available at https://github.com/THU-Kingmin/BAFlow.
| Type: | Proceedings paper |
|---|---|
| Title: | Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling |
| Event: | Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24) |
| ISBN-13: | 978-1-956792-04-1 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.24963/ijcai.2024/110 |
| Publisher version: | https://doi.org/10.24963/ijcai.2024/110 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Computer Vision: CV: Image and video synthesis and generation/ Computer Vision: CV: Applications |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10197873 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
