StylePart: Image-based Shape Part Manipulation
This addresses a lack of image-based part controllers for man-made shapes, offering a novel solution for intuitive editing tasks.
The paper tackles the problem of intuitive shape manipulation in images of man-made objects, such as resizing chair backrests or replacing cup handles, by presenting StylePart, a framework that enables direct shape manipulation through a shape-consistent latent mapping between image and 3D shape generative models.
Due to a lack of image-based "part controllers", shape manipulation of man-made shape images, such as resizing the backrest of a chair or replacing a cup handle is not intuitive. 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. We demonstrate our approach through various manipulation tasks, including part replacement, part resizing, and viewpoint manipulation, and evaluate its effectiveness through extensive ablation studies.