Presentation

<
RealFill: Reference-driven Generation for Authentic Image Completion
SessionControllable Image Generation and Completion
DescriptionGiven a few reference images that roughly capture the same scene, and a target image with a missing region, RealFill is able to complete the target image with high-quality image content that is faithful to the true scene.
Authors
Luming Tang
Cornell University
Nataniel Ruiz
Google Research
Qinghao Chu
Google Research
Yuanzhen Li
Google Research
Aleksander Holynski
Google Research
David E. Jacobs
Google Research
Bharath Hariharan
Cornell University
Yael Pritch
Google Research
Neal Wadhwa
Google Research
Kfir Aberman
Snap
Michael Rubinstein
Google Research
Event Type
Technical Paper
TimeThursday, 1 August 20249:40am - 9:50am MDT
LocationMile High 1
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Thursday, 1 August 20249:00am - 10:30am MDTMile High 1
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Thursday
Next PresentationNext PresentationObject-level Scene Deocclusion