Salvato in:
Dettagli Bibliografici
Autori principali: Li, Pengzhi, Huang, QInxuan, Ding, Yikang, Li, Zhiheng
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2305.18676
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916196925833216
author Li, Pengzhi
Huang, QInxuan
Ding, Yikang
Li, Zhiheng
author_facet Li, Pengzhi
Huang, QInxuan
Ding, Yikang
Li, Zhiheng
contents Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining consistency between the subject and the background remains challenging. In this paper, we propose LayerDiffusion, a semantic-based layered controlled image editing method. Our method enables non-rigid editing and attribute modification of specific subjects while preserving their unique characteristics and seamlessly integrating them into new backgrounds. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy combined with layered diffusion training. During the diffusion process, an iterative guidance strategy is used to generate a final image that aligns with the textual description. Experimental results demonstrate the effectiveness of our method in generating highly coherent images that closely align with the given textual description. The edited images maintain a high similarity to the features of the input image and surpass the performance of current leading image editing methods. LayerDiffusion opens up new possibilities for controllable image editing.
format Preprint
id arxiv_https___arxiv_org_abs_2305_18676
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LayerDiffusion: Layered Controlled Image Editing with Diffusion Models
Li, Pengzhi
Huang, QInxuan
Ding, Yikang
Li, Zhiheng
Computer Vision and Pattern Recognition
Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining consistency between the subject and the background remains challenging. In this paper, we propose LayerDiffusion, a semantic-based layered controlled image editing method. Our method enables non-rigid editing and attribute modification of specific subjects while preserving their unique characteristics and seamlessly integrating them into new backgrounds. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy combined with layered diffusion training. During the diffusion process, an iterative guidance strategy is used to generate a final image that aligns with the textual description. Experimental results demonstrate the effectiveness of our method in generating highly coherent images that closely align with the given textual description. The edited images maintain a high similarity to the features of the input image and surpass the performance of current leading image editing methods. LayerDiffusion opens up new possibilities for controllable image editing.
title LayerDiffusion: Layered Controlled Image Editing with Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.18676