Diffusion-Based Image-to-Image Translation by Noise Correction via Prompt Interpolation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Junsung, Kang, Minsoo, Han, Bohyung
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917774753792000
author Lee, Junsung
Kang, Minsoo
Han, Bohyung
author_facet Lee, Junsung
Kang, Minsoo
Han, Bohyung
contents We propose a simple but effective training-free approach tailored to diffusion-based image-to-image translation. Our approach revises the original noise prediction network of a pretrained diffusion model by introducing a noise correction term. We formulate the noise correction term as the difference between two noise predictions; one is computed from the denoising network with a progressive interpolation of the source and target prompt embeddings, while the other is the noise prediction with the source prompt embedding. The final noise prediction network is given by a linear combination of the standard denoising term and the noise correction term, where the former is designed to reconstruct must-be-preserved regions while the latter aims to effectively edit regions of interest relevant to the target prompt. Our approach can be easily incorporated into existing image-to-image translation methods based on diffusion models. Extensive experiments verify that the proposed technique achieves outstanding performance with low latency and consistently improves existing frameworks when combined with them.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08077
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion-Based Image-to-Image Translation by Noise Correction via Prompt Interpolation
Lee, Junsung
Kang, Minsoo
Han, Bohyung
Computer Vision and Pattern Recognition
We propose a simple but effective training-free approach tailored to diffusion-based image-to-image translation. Our approach revises the original noise prediction network of a pretrained diffusion model by introducing a noise correction term. We formulate the noise correction term as the difference between two noise predictions; one is computed from the denoising network with a progressive interpolation of the source and target prompt embeddings, while the other is the noise prediction with the source prompt embedding. The final noise prediction network is given by a linear combination of the standard denoising term and the noise correction term, where the former is designed to reconstruct must-be-preserved regions while the latter aims to effectively edit regions of interest relevant to the target prompt. Our approach can be easily incorporated into existing image-to-image translation methods based on diffusion models. Extensive experiments verify that the proposed technique achieves outstanding performance with low latency and consistently improves existing frameworks when combined with them.
title Diffusion-Based Image-to-Image Translation by Noise Correction via Prompt Interpolation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.08077