Neural Crossbreed: Neural Based Image Metamorphosis

TL;DR

Neural Crossbreed introduces a neural network that learns semantic transformations for image morphing, enabling high-quality, flexible transitions between images with different poses or styles without explicit correspondences.

Contribution

It is the first to utilize a pre-trained generative model for learning semantic image transformations in morphing tasks.

Findings

Produces high-quality morphed images

Handles significant pose and view differences

Enables applications like multi-image morphing and video interpolation

Abstract

We propose Neural Crossbreed, a feed-forward neural network that can learn a semantic change of input images in a latent space to create the morphing effect. Because the network learns a semantic change, a sequence of meaningful intermediate images can be generated without requiring the user to specify explicit correspondences. In addition, the semantic change learning makes it possible to perform the morphing between the images that contain objects with significantly different poses or camera views. Furthermore, just as in conventional morphing techniques, our morphing network can handle shape and appearance transitions separately by disentangling the content and the style transfer for rich usability. We prepare a training dataset for morphing using a pre-trained BigGAN, which generates an intermediate image by interpolating two latent vectors at an intended morphing value. This is the first attempt to address image morphing using a pre-trained generative model in order to learn semantic transformation. The experiments show that Neural Crossbreed produces high quality morphed images, overcoming various limitations associated with conventional approaches. In addition, Neural Crossbreed can be further extended for diverse applications such as multi-image morphing, appearance transfer, and video frame interpolation.