RsViT - A Scalable Vision Transformer Backbone for Diffusion Model.

Thanawin Sakpuaram Chantana Chantrapornchai

Published in: AINA (3) (2024)

Keyphrases

diffusion model
anisotropic diffusion
diffusion models
information diffusion
fuzzy logic
computer vision
diffusion process
influence maximization
laplace transform
image processing
diffusion tensor
random walk
collaborative learning
image sequences
denoising
high quality
decision making