Presentation

Cross-image Attention for Zero-shot Appearance Transfer
DescriptionOur zero-shot appearance transfer approach leverages the semantic understanding of text-to-image models to transfer visual appearance across semantically similar objects. Using our cross-image attention, we establish semantic correspondences between two images, combining one image's structure with another's appearance during generation. This allows transferring appearance across diverse inputs with no model training.
Event Type
Technical Paper
TimeThursday, 1 August 20243:55pm - 4:05pm MDT
LocationMile High 4
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Thursday, 1 August 20243:45pm - 5:15pm MDTMile High 4
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Thursday