Developing Diffusion Models with 3D World Knowledge to Enable Analysis by Synthesis

Abstract

The goal of this proposal is to create Diffusion Models with 3D world knowledge which can be used to develop novel computer vision algorithms using an analysis by synthsis perspective. This involves developing DMS which are prompted by the world state W and can generate images I from a model conditioned on the world state.

Document Details

Document Type
DoD Grant Award
Publication Date
Nov 09, 2024
Source ID
N000142412696

Entities

People

  • Alan Yuille

Organizations

  • Johns Hopkins University
  • Office of Naval Research
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • International Relations and European Studies
  • Theoretical Analysis.

Technology Areas

  • AI & ML