Session

<
Technical Paper: Controllable Image Generation and Completion
Session Chair
Cecilia Zhang
Adobe
University of California Berkeley
Event TypeTechnical Paper
TimeThursday, 1 August 20249:00am - 10:30am MDT
LocationMile High 1
Interest Areas
Research & Education
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Thursday
Presentations
9:00am - 9:10am MDTConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints
Authors
Elad Richardson
Kfir Goldberg
Yuval Alaluf
Daniel Cohen-Or
Presenter
Yuval Alaluf
Livestreamed
Recorded
9:10am - 9:20am MDTFilter-Guided Diffusion for Controllable Image Generation
Authors
Zeqi Gu
Ethan Yang
Abe Davis
Livestreamed
Recorded
9:20am - 9:30am MDTLOOSECONTROL: Lifting ControlNet for Generalized Depth Conditioning
Authors
Shariq Bhat
Niloy Mitra
Peter Wonka
Livestreamed
Recorded
9:30am - 9:40am MDTSeparate-and-Enhance: Compositional Finetuning for Text-to-image Diffusion Models
Authors
Zhipeng Bao
Yijun Li
Krishna Kumar Singh
Yu-Xiong Wang
Martial Hebert
Livestreamed
Recorded
9:40am - 9:50am MDTRealFill: Reference-driven Generation for Authentic Image Completion
Authors
Luming Tang
Nataniel Ruiz
Qinghao Chu
Yuanzhen Li
Aleksander Holynski
David E. Jacobs
Bharath Hariharan
Yael Pritch
Neal Wadhwa
Kfir Aberman
Michael Rubinstein
Livestreamed
Recorded
9:50am - 10:00am MDTObject-level Scene Deocclusion
Authors
Zhengzhe Liu
Qing Liu
Chirui Chang
Jianming Zhang
Daniil Pakhomov
Haitian Zheng
Zhe Lin
Daniel Cohen-Or
Chi-Wing Fu
Not Livestreamed
Not Recorded
10:00am - 10:30am MDTControllable Image Generation and Completion - Interactive Discussion
Not Livestreamed
Not Recorded