TY - GEN
T1 - Image Shape Manipulation from a Single Augmented Training Sample
AU - Vinker, Yael
AU - Horwitz, Eliahu
AU - Zabari, Nir
AU - Hoshen, Yedid
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.
AB - In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.
UR - http://www.scopus.com/inward/record.url?scp=85125925175&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.01351
DO - 10.1109/ICCV48922.2021.01351
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85125925175
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 13749
EP - 13758
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -