GroupDiff: Diffusion-based Group Portrait Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Yuming, Zhao, Nanxuan, Liu, Qing, Singh, Krishna Kumar, Yang, Shuai, Loy, Chen Change, Liu, Ziwei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910616570036224
author Jiang, Yuming
Zhao, Nanxuan
Liu, Qing
Singh, Krishna Kumar
Yang, Shuai
Loy, Chen Change
Liu, Ziwei
author_facet Jiang, Yuming
Zhao, Nanxuan
Liu, Qing
Singh, Krishna Kumar
Yang, Shuai
Loy, Chen Change
Liu, Ziwei
contents Group portrait editing is highly desirable since users constantly want to add a person, delete a person, or manipulate existing persons. It is also challenging due to the intricate dynamics of human interactions and the diverse gestures. In this work, we present GroupDiff, a pioneering effort to tackle group photo editing with three dedicated contributions: 1) Data Engine: Since there is no labeled data for group photo editing, we create a data engine to generate paired data for training. The training data engine covers the diverse needs of group portrait editing. 2) Appearance Preservation: To keep the appearance consistent after editing, we inject the images of persons from the group photo into the attention modules and employ skeletons to provide intra-person guidance. 3) Control Flexibility: Bounding boxes indicating the locations of each person are used to reweight the attention matrix so that the features of each person can be injected into the correct places. This inter-person guidance provides flexible manners for manipulation. Extensive experiments demonstrate that GroupDiff exhibits state-of-the-art performance compared to existing methods. GroupDiff offers controllability for editing and maintains the fidelity of the original photos.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14379
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GroupDiff: Diffusion-based Group Portrait Editing
Jiang, Yuming
Zhao, Nanxuan
Liu, Qing
Singh, Krishna Kumar
Yang, Shuai
Loy, Chen Change
Liu, Ziwei
Computer Vision and Pattern Recognition
Group portrait editing is highly desirable since users constantly want to add a person, delete a person, or manipulate existing persons. It is also challenging due to the intricate dynamics of human interactions and the diverse gestures. In this work, we present GroupDiff, a pioneering effort to tackle group photo editing with three dedicated contributions: 1) Data Engine: Since there is no labeled data for group photo editing, we create a data engine to generate paired data for training. The training data engine covers the diverse needs of group portrait editing. 2) Appearance Preservation: To keep the appearance consistent after editing, we inject the images of persons from the group photo into the attention modules and employ skeletons to provide intra-person guidance. 3) Control Flexibility: Bounding boxes indicating the locations of each person are used to reweight the attention matrix so that the features of each person can be injected into the correct places. This inter-person guidance provides flexible manners for manipulation. Extensive experiments demonstrate that GroupDiff exhibits state-of-the-art performance compared to existing methods. GroupDiff offers controllability for editing and maintains the fidelity of the original photos.
title GroupDiff: Diffusion-based Group Portrait Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.14379