Wired Perspectives: Multi-View Wire Art Embraces Generative AI
This work addresses the problem of making MVWA creation accessible to non-experts, though it appears incremental as it combines existing techniques like 3D Bézier curves and diffusion models.
The paper tackles the complex task of creating multi-view wire art (MVWA) sculptures by introducing DreamWire, an AI system that allows users to generate MVWA from text prompts or scribbles, achieving results that ensure spatial continuity and overcome data scarcity.
Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists. In response, we present DreamWire, an AI system enabling everyone to craft MVWA easily. Users express their vision through text prompts or scribbles, freeing them from intricate 3D wire organisation. Our approach synergises 3D Bézier curves, Prim's algorithm, and knowledge distillation from diffusion models or their variants (e.g., ControlNet). This blend enables the system to represent 3D wire art, ensuring spatial continuity and overcoming data scarcity. Extensive evaluation and analysis are conducted to shed insight on the inner workings of the proposed system, including the trade-off between connectivity and visual aesthetics.