A piece of History
We use an image-to-image translation network to encode motion priors of natural scenes collected from online videos so that for a new photo, we can synthesize a corresponding motion field. The image is then animated using the generated motion through a deep warping technique: pixels are encoded as deep features, those features are warped via Eulerian motion, and the resulting warped feature maps are decoded as images.
When MasterWorks meets AI and NFT
Nearly 200 uniques and extraordinary pieces of the Mona Lisa animated by Artificial Intelligence. At a time when we are witnessing the advent of Digital Art in the form of NFT, we have worked on a derivative work mixing graphic effects and the use of deep learning. It is the first time that this type of approach is realized in a major work of Art.
Discover Innovative Works
A General scene motion is highly complex, involving perspective effects, occlusions, and transience. Some pieces better interpreted by the AI have a higher value but it depends on your expectations as a Collector
