Image Morphing With Perceptual Constraints and STN Alignment

Simple item page
dc.contributor.authorFish, N.en_US
dc.contributor.authorZhang, R.en_US
dc.contributor.authorPerry, L.en_US
dc.contributor.authorCohen‐Or, D.en_US
dc.contributor.authorShechtman, E.en_US
dc.contributor.authorBarnes, C.en_US
dc.contributor.editorBenes, Bedrich and Hauser, Helwigen_US
dc.date.accessioned2020-10-06T16:54:02Z
dc.date.available2020-10-06T16:54:02Z
dc.date.issued2020
dc.description.abstractIn 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.en_US
dc.description.number6
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14027
dc.identifier.issn1467-8659
dc.identifier.pages303-313
dc.identifier.urihttps://doi.org/10.1111/cgf.14027
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14027
dc.publisher© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltden_US
dc.subjectimage morphing
dc.subjectgenerative adversarial networks
dc.subjectspatial transformers
dc.subjectperceptual similarity
dc.titleImage Morphing With Perceptual Constraints and STN Alignmenten_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v39i6pp303-313.pdf
Size:
1.41 MB
Format:
Adobe Portable Document Format
Download
Collections
39-Issue 6