Wired Perspectives: Multi-View Wire Art Embraces Generative AI

TL;DR

DreamWire is an AI system that simplifies the creation of multi-view wire art by translating user prompts into 3D wire sculptures, combining advanced algorithms and diffusion models for accessible artistic expression.

Contribution

The paper introduces DreamWire, a novel AI system that automates multi-view wire art creation from text or sketches, integrating 3D Bezier curves, Prim's algorithm, and knowledge distillation from diffusion models.

Findings

Effective representation of 3D wire art with spatial continuity

Successful translation of text prompts and scribbles into wire sculptures

Analysis of the trade-off between connectivity and visual aesthetics

Abstract

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 B\'ezier 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.