Wired Perspectives: Multi-View Wire Art Embraces Generative AI

TL;DR

This work tackles the challenge of generating multi-view wire art (MVWA) by introducing DreamWire, a system that produces 3D wire sculptures from per-view prompts provided as text or scribbles. It fuses differentiable 3D rendering of cubic Bézier wires with diffusion-prior supervision and multi-view conditioning (via ControlNet) to align each view with the user input, while enforcing connectivity through a minimum spanning tree regularization. The key contributions include a differentiable 3D MVWA rendering pipeline, an MST-based connectivity mechanism, and a practical pathway to physical realization, enabling quick, per-view-driven MVWA generation. The approach broadens access to AI-assisted abstract sculpture and offers insights into balancing connectivity and visual fidelity in view-dependent art.

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 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.

Figures (11)

• Figure 1: Multi-view art done generatively. We present DreamWire as the first system that takes user prompt for each view as input -- either via the expressive vehicle of text or image -- and produces 3D line sculptures showing distinct interpretations when viewed at different angles, i.e., multi-view wire art (MVWA). Compared to previous rule-based work, we significantly improve the quality of MVWA by utilising the flexible drawing capabilities of a universal generative prior (diffusion models or ControlNet). Notably, the "GBE" here pays tribute to the book "Gödel, Escher, Bach: an Eternal Golden Braid" GEB, which discusses how systems can acquire meaningful context despite being made of "meaningless" elements, just like what MVWA does.
• Figure 2: MVWA generated via DreamWire. The textual prompts employed predominantly include "a head of [character]" and "a simple drawing of [item]". Notably, all captions for these MVWA have been sourced from ChatGPT chatgpt. We prompt it to return three major subjects of interests under a given topic, e.g., three celebrated movie characters of the United States of America.
• Figure 3: Schematic overview of DreamWire. Starting from an initial set of random 3D Bézier curves, we project these curves onto a given 2D plane and process them into normal raster images. It follows that these images are fed into a generative diffusion model and optimised towards a visual target. In addition, we use the MST algorithm to constrain the distance between curves. Here we present a MVWA sample output under the condition $\{c^X, c^Y, c^Z\}=\{$"dog", "backpack", "cat"$\}$.
• Figure 4: Effect of the MST regularisation on a set of randomly initialised Bézier curves.
• Figure 5: Comparison with existing multi-view wire art synthesis methods. The user-specified visual controls are highlighted with red lines.