StylePart: image-based shape part manipulation

I‐Chao Shen

doi:10.1007/s00371-024-03310-9

StylePart: image-based shape part manipulation

2024-04-02

0

OA

AI

DOI：10.1007/s00371-024-03310-9

Original

Original request for help

Save

Abstract

En 中文

Direct part-level manipulation of man-made shapes in an image is desired given its simplicity. However, it is not intuitive given the existing manually created cuboid and cylinder controllers. To tackle this problem, we present StylePart, a framework that enables direct shape manipulation of an image by leveraging generative models of both images and 3D shapes. Our key contribution is a shape-consistent latent mapping function that connects the image generative latent space and the 3D man-made shape attribute latent space. Our method forwardly maps the image content to its corresponding 3D shape attributes, where the shape part can be easily manipulated. The attribute codes of the manipulated 3D shape are then backwardly mapped to the image latent code to obtain the final manipulated image. By using both forward and backward mapping, an user can edit the image directly without resorting to any 3D workflow. We demonstrate our approach through various manipulation tasks, including part replacement, part resizing, and shape orientation manipulation, and evaluate its effectiveness through extensive ablation studies.

Keywords:

Image editing

Image generative model

3D shape generative model

Latent vector mapping function

StylePart: image-based shape part manipulation

Abstract

Journal

Organization