ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3552-3560
DOI: 10.1609/aaai.v37i3.25465 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Zijian Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs). Their key idea is to disrupt images into noise through a fixed forward process and learn its reverse process to generate samples from noise in a denoising way. For conditional DDPMs, most existing practices relate conditions only to the reverse process and fit it to the reversal of unconditional forward process. We find this will limit the condition modeling and generation in a small time window. In this paper, we propose a novel and flexible conditional diffusion model by introducing conditions into the forward process. We utilize extra latent space to allocate an exclusive diffusion trajectory for each condition based on some shifting rules, which will disperse condition modeling to all timesteps and improve the learning capacity of model. We formulate our method, which we call ShiftDDPMs, and provide a unified point of view on existing related methods. Extensive qualitative and quantitative experiments on image synthesis demonstrate the feasibility and effectiveness of ShiftDDPMs.
Zitieren
APA
Zhang, Z., Zhao, Z., Yu, J., & Tian, Q. (2023). ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3552-3560. https://doi.org/10.1609/aaai.v37i3.25465
Vancouver
Zhang Z, Zhao Z, Yu J, Tian Q. ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3552-3560. doi:10.1609/aaai.v37i3.25465
BibTeX
@article{Zhang2023,
author = {Zhang, Zijian and Zhao, Zhou and Yu, Jun and Tian, Qi},
title = {ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {3},
pages = {3552--3560},
doi = {10.1609/aaai.v37i3.25465}
}
EUVIMED