RealFill: Reference-Driven Generation for Authentic Image Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Luming, Ruiz, Nataniel, Chu, Qinghao, Li, Yuanzhen, Holynski, Aleksander, Jacobs, David E., Hariharan, Bharath, Pritch, Yael, Wadhwa, Neal, Aberman, Kfir, Rubinstein, Michael
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910445351206912
author Tang, Luming
Ruiz, Nataniel
Chu, Qinghao
Li, Yuanzhen
Holynski, Aleksander
Jacobs, David E.
Hariharan, Bharath
Pritch, Yael
Wadhwa, Neal
Aberman, Kfir
Rubinstein, Michael
author_facet Tang, Luming
Ruiz, Nataniel
Chu, Qinghao
Li, Yuanzhen
Holynski, Aleksander
Jacobs, David E.
Hariharan, Bharath
Pritch, Yael
Wadhwa, Neal
Aberman, Kfir
Rubinstein, Michael
contents Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2309_16668
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RealFill: Reference-Driven Generation for Authentic Image Completion
Tang, Luming
Ruiz, Nataniel
Chu, Qinghao
Li, Yuanzhen
Holynski, Aleksander
Jacobs, David E.
Hariharan, Bharath
Pritch, Yael
Wadhwa, Neal
Aberman, Kfir
Rubinstein, Michael
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io
title RealFill: Reference-Driven Generation for Authentic Image Completion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
url https://arxiv.org/abs/2309.16668