3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Haoran, Ma, Long, Shi, Haolin, Hao, Yanbin, Liao, Yong, Cheng, Lechao, Zhou, Pengyuan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916332249808896
author Li, Haoran
Ma, Long
Shi, Haolin
Hao, Yanbin
Liao, Yong
Cheng, Lechao
Zhou, Pengyuan
author_facet Li, Haoran
Ma, Long
Shi, Haolin
Hao, Yanbin
Liao, Yong
Cheng, Lechao
Zhou, Pengyuan
contents The current GAN inversion methods typically can only edit the appearance and shape of a single object and background while overlooking spatial information. In this work, we propose a 3D editing framework, 3D-GOI, to enable multifaceted editing of affine information (scale, translation, and rotation) on multiple objects. 3D-GOI realizes the complex editing function by inverting the abundance of attribute codes (object shape/appearance/scale/rotation/translation, background shape/appearance, and camera pose) controlled by GIRAFFE, a renowned 3D GAN. Accurately inverting all the codes is challenging, 3D-GOI solves this challenge following three main steps. First, we segment the objects and the background in a multi-object image. Second, we use a custom Neural Inversion Encoder to obtain coarse codes of each object. Finally, we use a round-robin optimization algorithm to get precise codes to reconstruct the image. To the best of our knowledge, 3D-GOI is the first framework to enable multifaceted editing on multiple objects. Both qualitative and quantitative experiments demonstrate that 3D-GOI holds immense potential for flexible, multifaceted editing in complex multi-object scenes.Our project and code are released at https://3d-goi.github.io .
format Preprint
id arxiv_https___arxiv_org_abs_2311_12050
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle 3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing
Li, Haoran
Ma, Long
Shi, Haolin
Hao, Yanbin
Liao, Yong
Cheng, Lechao
Zhou, Pengyuan
Computer Vision and Pattern Recognition
The current GAN inversion methods typically can only edit the appearance and shape of a single object and background while overlooking spatial information. In this work, we propose a 3D editing framework, 3D-GOI, to enable multifaceted editing of affine information (scale, translation, and rotation) on multiple objects. 3D-GOI realizes the complex editing function by inverting the abundance of attribute codes (object shape/appearance/scale/rotation/translation, background shape/appearance, and camera pose) controlled by GIRAFFE, a renowned 3D GAN. Accurately inverting all the codes is challenging, 3D-GOI solves this challenge following three main steps. First, we segment the objects and the background in a multi-object image. Second, we use a custom Neural Inversion Encoder to obtain coarse codes of each object. Finally, we use a round-robin optimization algorithm to get precise codes to reconstruct the image. To the best of our knowledge, 3D-GOI is the first framework to enable multifaceted editing on multiple objects. Both qualitative and quantitative experiments demonstrate that 3D-GOI holds immense potential for flexible, multifaceted editing in complex multi-object scenes.Our project and code are released at https://3d-goi.github.io .
title 3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.12050