SEAN: Image Synthesis With Semantic Region-Adaptive Normalization
Type
Conference PaperKAUST Department
Computer ScienceComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Visual Computing Center (VCC)
Date
2020-08-05Online Publication Date
2020-08-05Print Publication Date
2020-06Permanent link to this record
http://hdl.handle.net/10754/664682
Metadata
Show full item recordAbstract
We propose semantic region-adaptive normalization (SEAN), a simple but effective building block for Generative Adversarial Networks conditioned on segmentation masks that describe the semantic regions in the desired output image. Using SEAN normalization, we can build a network architecture that can control the style of each semantic region individually, e.g., we can specify one style reference image per region. SEAN is better suited to encode, transfer, and synthesize style than the best previous method in terms of reconstruction quality, variability, and visual quality. We evaluate SEAN on multiple datasets and report better quantitative metrics (e.g. FID, PSNR) than the current state of the art. SEAN also pushes the frontier of interactive image editing. We can interactively edit images by changing segmentation masks or the style for any given region. We can also interpolate styles from two reference images per region.Citation
Zhu, P., Abdal, R., Qin, Y., & Wonka, P. (2020). SEAN: Image Synthesis With Semantic Region-Adaptive Normalization. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00515Conference/Event name
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)ISBN
978-1-7281-7169-2arXiv
1911.12861Additional Links
https://ieeexplore.ieee.org/document/9156510/https://ieeexplore.ieee.org/document/9156510/
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9156510
ae974a485f413a2113503eed53cd6c53
10.1109/CVPR42600.2020.00515