no code implementations • 30 Mar 2022 • Mohammed Alser, Sharon Waymost, Ram Ayyala, Brendan Lawlor, Richard J. Abdill, Neha Rajkumar, Nathan LaPierre, Jaqueline Brito, Andre M. Ribeiro-dos-Santos, Can Firtina, Nour Almadhoun, Varuni Sarwal, Eleazar Eskin, Qiyang Hu, Derek Strong, Byoung-Do, Kim, Malak S. Abedalthagafi, Onur Mutlu, Serghei Mangul
Omics software tools have reshaped the landscape of modern biology and become an essential component of biomedical research.
In this work, we propose a novel system for smart copy-paste, enabling the synthesis of high-quality results given a masked source image content and a target image context as input.
Because items in an image can be animated in arbitrarily many different ways, we introduce as control signal a sequence of motion strokes.
We study the problem of building models that can transfer selected attributes from one image to another without affecting the other attributes.
We present a novel system for sketch-based face image editing, enabling users to edit images intuitively by sketching a few strokes on a region of interest.
We learn our representation without any labeling or knowledge of the data domain, using an autoencoder architecture with two novel training objectives: first, we propose an invariance objective to encourage that encoding of each attribute, and decoding of each chunk, are invariant to changes in other attributes and chunks, respectively; second, we include a classification objective, which ensures that each chunk corresponds to a consistently discernible attribute in the represented image, hence avoiding degenerate feature mappings where some chunks are completely ignored.
Such models could be used to encode features that can efficiently be used for classification and to transfer attributes between different images in image synthesis.