LSDM
Language-driven Scene Synthesis using Multi-conditional Diffusion Model
2000년 도입 · 논문 1편에서 사용
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.
Diffusion Models · General3D Representations · Computer Vision