Inpainting-Driven Mask Optimization for Object Removal

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shimosato, Kodai, Ukita, Norimichi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910379836178432
author Shimosato, Kodai
Ukita, Norimichi
author_facet Shimosato, Kodai
Ukita, Norimichi
contents This paper proposes a mask optimization method for improving the quality of object removal using image inpainting. While many inpainting methods are trained with a set of random masks, a target for inpainting may be an object, such as a person, in many realistic scenarios. This domain gap between masks in training and inference images increases the difficulty of the inpainting task. In our method, this domain gap is resolved by training the inpainting network with object masks extracted by segmentation, and such object masks are also used in the inference step. Furthermore, to optimize the object masks for inpainting, the segmentation network is connected to the inpainting network and end-to-end trained to improve the inpainting performance. The effect of this end-to-end training is further enhanced by our mask expansion loss for achieving the trade-off between large and small masks. Experimental results demonstrate the effectiveness of our method for better object removal using image inpainting.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Inpainting-Driven Mask Optimization for Object Removal
Shimosato, Kodai
Ukita, Norimichi
Computer Vision and Pattern Recognition
This paper proposes a mask optimization method for improving the quality of object removal using image inpainting. While many inpainting methods are trained with a set of random masks, a target for inpainting may be an object, such as a person, in many realistic scenarios. This domain gap between masks in training and inference images increases the difficulty of the inpainting task. In our method, this domain gap is resolved by training the inpainting network with object masks extracted by segmentation, and such object masks are also used in the inference step. Furthermore, to optimize the object masks for inpainting, the segmentation network is connected to the inpainting network and end-to-end trained to improve the inpainting performance. The effect of this end-to-end training is further enhanced by our mask expansion loss for achieving the trade-off between large and small masks. Experimental results demonstrate the effectiveness of our method for better object removal using image inpainting.
title Inpainting-Driven Mask Optimization for Object Removal
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.15849