Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems
PASEO (Perturb-And-Solve for Efficient Operator conditioning), a method that uses a small (1M parameters) learned network to degrade diffusion model predictions in latent space, achieves strong perceptual quality while running up to 9x faster and using up to 34% less peak memory than the tested baselines.
Abduragim Shtanchaev, A. Asadulaev, Luiza Labazanova et al.
· 0 citations