Creating cinemagraphs from a single image
AssigneeAdobe Inc.
InventorsDuygu Ceylan Aksit, Hugo Bertiche Argila, Niloy Jyoti Mitra, Kuldeep Kulkarni, Chun Hao Huang, Yangtuanfeng Wang
Life of this patent
Estimating the term…
Loading patent…
AssigneeAdobe Inc.
InventorsDuygu Ceylan Aksit, Hugo Bertiche Argila, Niloy Jyoti Mitra, Kuldeep Kulkarni, Chun Hao Huang, Yangtuanfeng Wang
Estimating the term…
The present disclosure relates to systems, methods, and non-transitory computer readable media that utilizes neural networks to generate cinemagraphs from single RGB images. For example, the cyclic animation system includes a cyclic animation neural network trained with synthetic data, wherein different wind effects can be replicated using physically based simulations to create cyclic videos more efficiently. More specifically, the cyclic animation system generalizes a solution by operating in the gradient domain and using surface normal maps. Because normal maps are invariant to appearance (color, texture, illumination, etc.), the gap between synthetic and real data distribution in the normal map space is smaller than in the RGB space. The cyclic animation system performs a reshading approach that synthesizes RGB pixels from the original image and the animated normal maps to create plausible changes to the real image to create the cinemagraph.
A computer-implemented method comprising:
A system comprising:
A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
Dependencies are inferred from the claim text.