Semantic image manipulation using visual-semantic joint embeddings
AssigneeAdobe Inc.
InventorsZhe Lin, Xihui Liu, Quan Hung Tran, Jianming Zhang, Handong Zhao
Life of this patent
Estimating the term…
Loading patent…
AssigneeAdobe Inc.
InventorsZhe Lin, Xihui Liu, Quan Hung Tran, Jianming Zhang, Handong Zhao
Estimating the term…
The technology described herein is directed to a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.
One or more non-transitory computer readable storage media having a semantic image manipulation agent stored thereon, the semantic image manipulation agent including program instructions that, when executed by one or more processors, direct the one or more processors to:
A method of performing unsupervised open-vocabulary semantic image manipulation, the method comprising:
A semantic image manipulation system, the system comprising:
Dependencies are inferred from the claim text.