Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Jeongsol, Kim, Beomsu, Ye, Jong Chul
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910708865695744
author Kim, Jeongsol
Kim, Beomsu
Ye, Jong Chul
author_facet Kim, Jeongsol
Kim, Beomsu
Ye, Jong Chul
contents Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. However, they often require a larger number of neural function evaluations (NFEs), limiting their practical applicability. In this paper, we tackle this problem with Schrodinger Bridges (SBs), which are stochastic differential equations (SDEs) between distributions with minimal transport cost. We analyze the probability flow ordinary differential equation (ODE) formulation of SBs, and observe that we can decompose its vector field into a linear combination of source predictor, target predictor, and noise predictor. Inspired by this observation, we propose Latent Schrodinger Bridges (LSBs) that approximate the SB ODE via pre-trained Stable Diffusion, and develop appropriate prompt optimization and change of variables formula to match the training and inference between distributions. We demonstrate that our algorithm successfully conduct competitive I2I translation in unsupervised setting with only a fraction of computation cost required by previous DM-based I2I methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14863
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
Kim, Jeongsol
Kim, Beomsu
Ye, Jong Chul
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. However, they often require a larger number of neural function evaluations (NFEs), limiting their practical applicability. In this paper, we tackle this problem with Schrodinger Bridges (SBs), which are stochastic differential equations (SDEs) between distributions with minimal transport cost. We analyze the probability flow ordinary differential equation (ODE) formulation of SBs, and observe that we can decompose its vector field into a linear combination of source predictor, target predictor, and noise predictor. Inspired by this observation, we propose Latent Schrodinger Bridges (LSBs) that approximate the SB ODE via pre-trained Stable Diffusion, and develop appropriate prompt optimization and change of variables formula to match the training and inference between distributions. We demonstrate that our algorithm successfully conduct competitive I2I translation in unsupervised setting with only a fraction of computation cost required by previous DM-based I2I methods.
title Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.14863