ReMOVE: A Reference-free Metric for Object Erasure
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917766092554240 |
|---|---|
| author | Chandrasekar, Aditya Chakrabarty, Goirik Bardhan, Jai Hebbalaguppe, Ramya AP, Prathosh |
| author_facet | Chandrasekar, Aditya Chakrabarty, Goirik Bardhan, Jai Hebbalaguppe, Ramya AP, Prathosh |
| contents | We introduce $\texttt{ReMOVE}$, a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measures such as LPIPS and CLIPScore, $\texttt{ReMOVE}$ addresses the challenge of evaluating inpainting without a reference image, common in practical scenarios. It effectively distinguishes between object removal and replacement. This is a key issue in diffusion models due to stochastic nature of image generation. Traditional metrics fail to align with the intuitive definition of inpainting, which aims for (1) seamless object removal within masked regions (2) while preserving the background continuity. $\texttt{ReMOVE}$ not only correlates with state-of-the-art metrics and aligns with human perception but also captures the nuanced aspects of the inpainting process, providing a finer-grained evaluation of the generated outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00707 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReMOVE: A Reference-free Metric for Object Erasure Chandrasekar, Aditya Chakrabarty, Goirik Bardhan, Jai Hebbalaguppe, Ramya AP, Prathosh Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We introduce $\texttt{ReMOVE}$, a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measures such as LPIPS and CLIPScore, $\texttt{ReMOVE}$ addresses the challenge of evaluating inpainting without a reference image, common in practical scenarios. It effectively distinguishes between object removal and replacement. This is a key issue in diffusion models due to stochastic nature of image generation. Traditional metrics fail to align with the intuitive definition of inpainting, which aims for (1) seamless object removal within masked regions (2) while preserving the background continuity. $\texttt{ReMOVE}$ not only correlates with state-of-the-art metrics and aligns with human perception but also captures the nuanced aspects of the inpainting process, providing a finer-grained evaluation of the generated outputs. |
| title | ReMOVE: A Reference-free Metric for Object Erasure |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.00707 |