English

Image Morphing with Perceptual Constraints and STN Alignment

Graphics 2020-05-05 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

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 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.

Keywords

Cite

@article{arxiv.2004.14071,
  title  = {Image Morphing with Perceptual Constraints and STN Alignment},
  author = {Noa Fish and Richard Zhang and Lilach Perry and Daniel Cohen-Or and Eli Shechtman and Connelly Barnes},
  journal= {arXiv preprint arXiv:2004.14071},
  year   = {2020}
}
R2 v1 2026-06-23T15:10:42.261Z