TY - JOUR
T1 - Image Morphing With Perceptual Constraints and STN Alignment
AU - Fish, N.
AU - Zhang, R.
AU - Perry, L.
AU - Cohen-Or, D.
AU - Shechtman, E.
AU - Barnes, C.
N1 - Publisher Copyright: © 2020 The Authors Computer Graphics Forum © 2020 Eurographics - The European Association for Computer Graphics and John Wiley & Sons Ltd
PY - 2020/9/1
Y1 - 2020/9/1
N2 - In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set and maintain a well-paced visual transition from one to the next. In this paper, we propose a conditional generative adversarial network (GAN) morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid-based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self-supervision, our network learns to generate visually pleasing morphing effects featuring believable in-betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.
AB - In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set and maintain a well-paced visual transition from one to the next. In this paper, we propose a conditional generative adversarial network (GAN) morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid-based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self-supervision, our network learns to generate visually pleasing morphing effects featuring believable in-betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.
KW - generative adversarial networks
KW - image morphing
KW - perceptual similarity
KW - spatial transformers
UR - http://www.scopus.com/inward/record.url?scp=85085697531&partnerID=8YFLogxK
U2 - https://doi.org/10.1111/cgf.14027
DO - https://doi.org/10.1111/cgf.14027
M3 - مقالة
SN - 0167-7055
VL - 39
SP - 303
EP - 313
JO - Computer Graphics Forum
JF - Computer Graphics Forum
IS - 6
ER -