MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Honghua, Lan, Yushi, Chen, Yongwei, Zhou, Yifan, Pan, Xingang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909357918126080
author Chen, Honghua
Lan, Yushi
Chen, Yongwei
Zhou, Yifan
Pan, Xingang
author_facet Chen, Honghua
Lan, Yushi
Chen, Yongwei
Zhou, Yifan
Pan, Xingang
contents Drag-based editing has become popular in 2D content creation, driven by the capabilities of image generative models. However, extending this technique to 3D remains a challenge. Existing 3D drag-based editing methods, whether employing explicit spatial transformations or relying on implicit latent optimization within limited-capacity 3D generative models, fall short in handling significant topology changes or generating new textures across diverse object categories. To overcome these limitations, we introduce MVDrag3D, a novel framework for more flexible and creative drag-based 3D editing that leverages multi-view generation and reconstruction priors. At the core of our approach is the usage of a multi-view diffusion model as a strong generative prior to perform consistent drag editing over multiple rendered views, which is followed by a reconstruction model that reconstructs 3D Gaussians of the edited object. While the initial 3D Gaussians may suffer from misalignment between different views, we address this via view-specific deformation networks that adjust the position of Gaussians to be well aligned. In addition, we propose a multi-view score function that distills generative priors from multiple views to further enhance the view consistency and visual quality. Extensive experiments demonstrate that MVDrag3D provides a precise, generative, and flexible solution for 3D drag-based editing, supporting more versatile editing effects across various object categories and 3D representations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16272
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
Chen, Honghua
Lan, Yushi
Chen, Yongwei
Zhou, Yifan
Pan, Xingang
Computer Vision and Pattern Recognition
Drag-based editing has become popular in 2D content creation, driven by the capabilities of image generative models. However, extending this technique to 3D remains a challenge. Existing 3D drag-based editing methods, whether employing explicit spatial transformations or relying on implicit latent optimization within limited-capacity 3D generative models, fall short in handling significant topology changes or generating new textures across diverse object categories. To overcome these limitations, we introduce MVDrag3D, a novel framework for more flexible and creative drag-based 3D editing that leverages multi-view generation and reconstruction priors. At the core of our approach is the usage of a multi-view diffusion model as a strong generative prior to perform consistent drag editing over multiple rendered views, which is followed by a reconstruction model that reconstructs 3D Gaussians of the edited object. While the initial 3D Gaussians may suffer from misalignment between different views, we address this via view-specific deformation networks that adjust the position of Gaussians to be well aligned. In addition, we propose a multi-view score function that distills generative priors from multiple views to further enhance the view consistency and visual quality. Extensive experiments demonstrate that MVDrag3D provides a precise, generative, and flexible solution for 3D drag-based editing, supporting more versatile editing effects across various object categories and 3D representations.
title MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.16272