Presentation
Blind Inversion using Latent Diffusion Priors
SessionInvited: Posters
DescriptionLatentDEM addresses the challenge of blind inverse problems by employing latent diffusion priors within an iterative Expectation-Maximization framework to jointly estimate signals and unknown forward operators, particularly for pose-free sparse-view 3D reconstruction. Supplementally, we introduce VLM3D, which leverages Vision-Language Models as semantic critics to correct fine-grained details missed by generative priors.
Event Type
Invited Poster
Poster
TimeThursday, 18 December 20259:00am - 6:00pm HKT
LocationChancellor 1+2, Level 4