TY - JOUR
T1 - Breaking the cycle-Colleagues are all you need
AU - Nizan, Ori
AU - Tal, Ayellet
N1 - Funding Information: We gratefully acknowledge the support of the Israel Science Foundation (ISF) 1083/18, PMRIPeter Munk Research Institute-Technion, and NVIDIA Corporation with the donation of the GPU. Funding Information: Furthermore, the paper proposes an implementation of this concept and demonstrates its benefits for three challenging applications. The members of the council generate several optional results for a given input. They manage to remove large objects from the images, not to leave redundant traces from the input and to handle large shape modifications. The results outperform those of SOTA algorithms both quantitatively and qualitatively. Acknowledgements: We gratefully acknowledge the support of the Israel Science Foundation (ISF) 1083/18, PMRI-Peter Munk Research Institute–Technion, and NVIDIA Corporation with the donation of the GPU. Publisher Copyright: © 2020 IEEE
PY - 2020
Y1 - 2020
N2 - This paper proposes a novel approach to performing image-to-image translation between unpaired domains. Rather than relying on a cycle constraint, our method takes advantage of collaboration between various GANs. This results in a multi-modal method, in which multiple optional and diverse images are produced for a given image. Our model addresses some of the shortcomings of classical GANs: (1) It is able to remove large objects, such as glasses. (2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image. (3) It manages to translate between domains that require large shape modifications. Our results are shown to outperform those generated by state-of-the-art methods for several challenging applications.
AB - This paper proposes a novel approach to performing image-to-image translation between unpaired domains. Rather than relying on a cycle constraint, our method takes advantage of collaboration between various GANs. This results in a multi-modal method, in which multiple optional and diverse images are produced for a given image. Our model addresses some of the shortcomings of classical GANs: (1) It is able to remove large objects, such as glasses. (2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image. (3) It manages to translate between domains that require large shape modifications. Our results are shown to outperform those generated by state-of-the-art methods for several challenging applications.
UR - https://www.scopus.com/pages/publications/85088115412
U2 - 10.1109/CVPR42600.2020.00788
DO - 10.1109/CVPR42600.2020.00788
M3 - Conference article
SN - 1063-6919
SP - 7857
EP - 7866
JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
M1 - 9156485
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Y2 - 14 June 2020 through 19 June 2020
ER -