BBDM: Image-to-image translation with Brownian bridge diffusion models

Li, Bo, Xue, Kaitao, Lui, Bin and Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 2023. BBDM: Image-to-image translation with Brownian bridge diffusion models. Presented at: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 18-22 June 2023. Proceedings of Conference on Computer Vision and Pattern Recognition. , vol.2023 IEEE, pp. 1952-1961. 10.1109/CVPR52729.2023.00194

Preview

PDF - Accepted Post-Print Version Download (8MB) | Preview

Abstract

Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the existing diffusion models treat image-to-image translation as conditional generation processes, and suffer heavily from the gap between distinct domains. In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian Bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process. To the best of our knowledge, it is the first work that proposes Brownian Bridge diffusion process for image-to-image translation. Experimental results on various benchmarks demonstrate that the proposed BBDM model achieves competitive performance through both visual inspection and measurable metrics.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	IEEE
ISBN:	9798350301304
ISSN:	1063-6919
Date of First Compliant Deposit:	20 April 2023
Date of Acceptance:	27 February 2023
Last Modified:	12 Dec 2023 13:22
URI:	https://orca.cardiff.ac.uk/id/eprint/158968

Actions (repository staff only)

Edit Item