Wired Perspectives: Multi-View Wire Art Embraces Generative AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Zhiyu, Yang, Lan, Zhang, Honggang, Xiang, Tao, Pang, Kaiyue, Song, Yi-Zhe
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911916533743616
author Qu, Zhiyu
Yang, Lan
Zhang, Honggang
Xiang, Tao
Pang, Kaiyue
Song, Yi-Zhe
author_facet Qu, Zhiyu
Yang, Lan
Zhang, Honggang
Xiang, Tao
Pang, Kaiyue
Song, Yi-Zhe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15421
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Wired Perspectives: Multi-View Wire Art Embraces Generative AI
Qu, Zhiyu
Yang, Lan
Zhang, Honggang
Xiang, Tao
Pang, Kaiyue
Song, Yi-Zhe
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Wired Perspectives: Multi-View Wire Art Embraces Generative AI
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2311.15421