ICTS:32492

Posterior Sampling for Image Personalization and Editing

(2025). Posterior Sampling for Image Personalization and Editing. SciVideos. https://scivideos.org/icts-tifr/32492

Posterior Sampling for Image Personalization and Editing. SciVideos, Aug. 11, 2025, https://scivideos.org/icts-tifr/32492 

          @misc{ scivideos_ICTS:32492,
            doi = {},
            url = {https://scivideos.org/icts-tifr/32492},
            author = {},
            keywords = {},
            language = {en},
            title = {Posterior Sampling for Image Personalization and Editing},
            publisher = {},
            year = {2025},
            month = {aug},
            note = {ICTS:32492 see, \url{https://scivideos.org/icts-tifr/32492}}
          }
Sanjay Shakkottai
Talk numberICTS:32492
Source RepositoryICTS-TIFR

Abstract

This talk will consist of two parts: In the first part, we will present an overview of posterior sampling with diffusion models, and motivate the connection to inverse problems. Specific topics that we will cover include Gibbs sampling, Importance sampling and approximations for test-time optimization (aka training-free approaches such as DPS) with diffusion models. In the second part, we will discuss algorithms for image editing, stylization, etc, that are in production in large-scale settings. Specifically, we will discuss both diffusion and flow-based algorithms (PSLD, STSL, RB Modulation, RF Inversion) that operate in the latent space of SOTA foundation models (such as Stable Diffusion or Flux).

Diffusions class videos are posted on YouTube (and lecture notes link is also posted in the video caption). Link: https://www.youtube.com/@ifml9883/playlists