Saved in:
Bibliographic Details
Main Authors: Bodur, Rumeysa, Bhattarai, Binod, Kim, Tae-Kyun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.13081
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915069095313408
author Bodur, Rumeysa
Bhattarai, Binod
Kim, Tae-Kyun
author_facet Bodur, Rumeysa
Bhattarai, Binod
Kim, Tae-Kyun
contents Text-guided image editing finds applications in various creative and practical fields. While recent studies in image generation have advanced the field, they often struggle with the dual challenges of coherent image transformation and context preservation. In response, our work introduces prompt augmentation, a method amplifying a single input prompt into several target prompts, strengthening textual context and enabling localised image editing. Specifically, we use the augmented prompts to delineate the intended manipulation area. We propose a Contrastive Loss tailored to driving effective image editing by displacing edited areas and drawing preserved regions closer. Acknowledging the continuous nature of image manipulations, we further refine our approach by incorporating the similarity concept, creating a Soft Contrastive Loss. The new losses are incorporated to the diffusion model, demonstrating improved or competitive image editing results on public datasets and generated images over state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13081
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prompt Augmentation for Self-supervised Text-guided Image Manipulation
Bodur, Rumeysa
Bhattarai, Binod
Kim, Tae-Kyun
Computer Vision and Pattern Recognition
Text-guided image editing finds applications in various creative and practical fields. While recent studies in image generation have advanced the field, they often struggle with the dual challenges of coherent image transformation and context preservation. In response, our work introduces prompt augmentation, a method amplifying a single input prompt into several target prompts, strengthening textual context and enabling localised image editing. Specifically, we use the augmented prompts to delineate the intended manipulation area. We propose a Contrastive Loss tailored to driving effective image editing by displacing edited areas and drawing preserved regions closer. Acknowledging the continuous nature of image manipulations, we further refine our approach by incorporating the similarity concept, creating a Soft Contrastive Loss. The new losses are incorporated to the diffusion model, demonstrating improved or competitive image editing results on public datasets and generated images over state-of-the-art approaches.
title Prompt Augmentation for Self-supervised Text-guided Image Manipulation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.13081