Viet-Anh on Software Logo

What is: Language-driven Scene Synthesis using Multi-conditional Diffusion Model?

Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Our main contribution is the Guiding Points Network, where we integrate all information from the conditions to generate guiding points. By applying transformation matrices to scene entities (human/objects) with attention weighting, we can forecast the spanning of the target object.