MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Kangneng, Gao, Daiheng, Wang, Xuan, Zhang, Jie, Zhang, Peng, Sun, Xusen, Zhang, Longhao, Yang, Shiqi, Zhang, Bang, Bo, Liefeng, Wang, Yaxing, Cheng, Ming-Ming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929410029912064
author Zhou, Kangneng
Gao, Daiheng
Wang, Xuan
Zhang, Jie
Zhang, Peng
Sun, Xusen
Zhang, Longhao
Yang, Shiqi
Zhang, Bang
Bo, Liefeng
Wang, Yaxing
Cheng, Ming-Ming
author_facet Zhou, Kangneng
Gao, Daiheng
Wang, Xuan
Zhang, Jie
Zhang, Peng
Sun, Xusen
Zhang, Longhao
Yang, Shiqi
Zhang, Bang
Bo, Liefeng
Wang, Yaxing
Cheng, Ming-Ming
contents 3D-aware portrait editing has a wide range of applications in multiple fields. However, current approaches are limited due that they can only perform mask-guided or text-based editing. Even by fusing the two procedures into a model, the editing quality and stability cannot be ensured. To address this limitation, we propose \textbf{MaTe3D}: mask-guided text-based 3D-aware portrait editing. In this framework, first, we introduce a new SDF-based 3D generator which learns local and global representations with proposed SDF and density consistency losses. This enhances masked-based editing in local areas; second, we present a novel distillation strategy: Conditional Distillation on Geometry and Texture (CDGT). Compared to exiting distillation strategies, it mitigates visual ambiguity and avoids mismatch between texture and geometry, thereby producing stable texture and convincing geometry while editing. Additionally, we create the CatMask-HQ dataset, a large-scale high-resolution cat face annotation for exploration of model generalization and expansion. We perform expensive experiments on both the FFHQ and CatMask-HQ datasets to demonstrate the editing quality and stability of the proposed method. Our method faithfully generates a 3D-aware edited face image based on a modified mask and a text prompt. Our code and models will be publicly released.
format Preprint
id arxiv_https___arxiv_org_abs_2312_06947
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
Zhou, Kangneng
Gao, Daiheng
Wang, Xuan
Zhang, Jie
Zhang, Peng
Sun, Xusen
Zhang, Longhao
Yang, Shiqi
Zhang, Bang
Bo, Liefeng
Wang, Yaxing
Cheng, Ming-Ming
Computer Vision and Pattern Recognition
3D-aware portrait editing has a wide range of applications in multiple fields. However, current approaches are limited due that they can only perform mask-guided or text-based editing. Even by fusing the two procedures into a model, the editing quality and stability cannot be ensured. To address this limitation, we propose \textbf{MaTe3D}: mask-guided text-based 3D-aware portrait editing. In this framework, first, we introduce a new SDF-based 3D generator which learns local and global representations with proposed SDF and density consistency losses. This enhances masked-based editing in local areas; second, we present a novel distillation strategy: Conditional Distillation on Geometry and Texture (CDGT). Compared to exiting distillation strategies, it mitigates visual ambiguity and avoids mismatch between texture and geometry, thereby producing stable texture and convincing geometry while editing. Additionally, we create the CatMask-HQ dataset, a large-scale high-resolution cat face annotation for exploration of model generalization and expansion. We perform expensive experiments on both the FFHQ and CatMask-HQ datasets to demonstrate the editing quality and stability of the proposed method. Our method faithfully generates a 3D-aware edited face image based on a modified mask and a text prompt. Our code and models will be publicly released.
title MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.06947