PartSticker: Generating Parts of Objects for Rapid Prototyping

Mo Zhou, Josh Myers-Dean, Danna Gurari

Keywords: diffusion, text-to-image, shape analysis

Abstract: Design prototyping involves creating mockups of products or concepts to gather feedback and iterate on ideas. While prototyping often requires specific parts of objects, such as when constructing a novel creature for a video game, existing text-to-image methods tend to only generate entire objects. To address this, we propose a novel task and method of "part sticker generation", which entails generating an isolated part of an object on a neutral background. Experiments demonstrate our method outperforms state-of-the-art baselines with respect to realism and text alignment, while preserving object-level generation capabilities. We release our code and models at https://anonymous.com to encourage community-wide progress on this new task.

Submission Number: 21