PartStickers: Generating Parts of Objects for Rapid Prototyping

2025-04-07

AI Summary

To address the need for rapid generation of localized object parts (e.g., wings of game creatures, joints of robotic arms) in design prototyping, this paper introduces and formally defines the novel task of *part sticker generation*: synthesizing semantically precise, high-fidelity, isolated part images against neutral backgrounds. Methodologically, we propose a diffusion-based conditional generation framework featuring four key innovations: (1) part-aware text encoding, (2) background-decoupled rendering, (3) part-mask-guided synthesis, and (4) local–global alignment loss. These components jointly enable fine-grained, controllable part-level generation while preserving compatibility with full-object synthesis and ensuring cross-scale consistency. Extensive experiments demonstrate significant improvements over state-of-the-art methods on realism and text-alignment metrics. To foster community advancement, our code and models are publicly released.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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 publicly share our code and models to encourage community-wide progress on this new task: https://partsticker.github.io.

Problem

• Generating isolated object parts for prototyping
• Improving realism and text alignment in part generation
• Enhancing object-level generation capabilities

Innovation

• Generates isolated object parts on neutral backgrounds
• Outperforms baselines in realism and text alignment
• Publicly shares code and models for community progress