Guardado en:
Detalles Bibliográficos
Autores principales: Stefanache, Stefan, Pérez, Lluís Pastor, Watanabe, Julen Costa, Tejedor, Ernesto Sanchez, Hofmann, Thomas, Simsar, Enis
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.05710
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913537399455744
author Stefanache, Stefan
Pérez, Lluís Pastor
Watanabe, Julen Costa
Tejedor, Ernesto Sanchez
Hofmann, Thomas
Simsar, Enis
author_facet Stefanache, Stefan
Pérez, Lluís Pastor
Watanabe, Julen Costa
Tejedor, Ernesto Sanchez
Hofmann, Thomas
Simsar, Enis
contents Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While recent developments in generative models have opened up previously unheard-of possibilities for image editing, conducting a thorough evaluation of these models remains a challenging and open task. The absence of a standardized evaluation benchmark, primarily due to the inherent need for a post-edit reference image for evaluation, further complicates this issue. Currently, evaluations often rely on established models such as CLIP or require human intervention for a comprehensive understanding of the performance of these image editing models. Our benchmark, PixLens, provides a comprehensive evaluation of both edit quality and latent representation disentanglement, contributing to the advancement and refinement of existing methodologies in the field.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAM
Stefanache, Stefan
Pérez, Lluís Pastor
Watanabe, Julen Costa
Tejedor, Ernesto Sanchez
Hofmann, Thomas
Simsar, Enis
Computer Vision and Pattern Recognition
Artificial Intelligence
Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While recent developments in generative models have opened up previously unheard-of possibilities for image editing, conducting a thorough evaluation of these models remains a challenging and open task. The absence of a standardized evaluation benchmark, primarily due to the inherent need for a post-edit reference image for evaluation, further complicates this issue. Currently, evaluations often rely on established models such as CLIP or require human intervention for a comprehensive understanding of the performance of these image editing models. Our benchmark, PixLens, provides a comprehensive evaluation of both edit quality and latent representation disentanglement, contributing to the advancement and refinement of existing methodologies in the field.
title PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAM
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.05710