Wired Perspectives: Multi-View Wire Art Embraces Generative AI
Zhiyu Qu, Lan Yang, Honggang Zhang, Tao Xiang, Kaiyue Pang, Yi-Zhe Song
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper10
- ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics SynthesisChuang Wang, Haitao Zhou, Ling Luo, Qian YuNeurIPS 2025 · 被引用 5 次
- ShadowDraw: From Any Object to Shadow-Drawing Compositional ArtRundong Luo, Noah Snavely, Wei-Chiu MaCVPR 2026 · 被引用 1 次
- WIR3D: Visually-Informed and Geometry-Aware 3D Shape AbstractionRichard Liu, Daniel Fu, Noah Tan, Itai Lang 等ICCV 2025 · 被引用 1 次
- Hand-Shadow PoserHao Xu, Yinqiao Wang, Niloy J. Mitra, Shuaicheng Liu 等SIGGRAPH 2025 · 被引用 1 次
- Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve RenderingYibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu 等ICLR 2025
它引用的顶会 Paper20
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou 等ICCV 2021 · 被引用 8,921 次
相关 Paper
- Fabricable 3D Wire ArtKenji Tojo, Ariel Shamir, Bernd Bickel, Nobuyuki UmetaniSIGGRAPH 2024 · 被引用 16 次
- WireRoom: model-guided explorative design of abstract wire artZhijin Yang, Pengfei Xu, Hongbo Fu, Hui HuangSIGGRAPH 2021 · 被引用 10 次
- CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe GenerationXueqi Ma, Yilin Liu, Tianlong Gao, Qirui Huang 等SIGGRAPH 2025 · 被引用 2 次
- MVDream: Multi-view Diffusion for 3D GenerationYichun Shi, Peng Wang, Jianglong Ye, Long Mai 等ICLR 2024 · 被引用 973 次
- SketchDream: Sketch-based Text-To-3D Generation and EditingFeng-Lin Liu, Hongbo Fu, Yu-Kun Lai, Lin GaoSIGGRAPH 2024 · 被引用 30 次
