Image Morphing with Perceptual Constraints and STN Alignment
arXiv:2004.14071 · doi:10.1111/cgf.14027
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.
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- ShapeNet: An Information-Rich 3D Model Repository
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- A Learned Representation For Artistic Style
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Large Scale Adversarial Representation Learning
- IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
- Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
- Neural Best-Buddies: Sparse Cross-Domain Correspondence
- ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learning