arXiv：cs.AI· Junyu Deng, Jiale Cao, Mengtian Li, Zhongxia Ji, Ruhua Chen, Yiyi He, Guangnan Ye, Zuo Hu·· 4 小时前
AuraLuxMuse：结合音乐与专家引导的自适应融合舞台灯光设计建模
AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance
AI 导读
AuraLuxMuse 是一个自动化美学舞台灯光设计系统，通过 Lighting-Aligned Music Pretraining（LAMP）对音频与灯光提示做对比学习对齐，并以 Preference-Adaptive Mixture of Experts（PAMoE）按设计师意图驱动偏好感知的提示检索与适配，返回可编辑提示而非取代设计师。
正文
Abstract:We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and preference-adaptive modeling. Lighting design in live performance settings requires the seamless translation of musical features into dynamic lighting behaviors. However, traditional workflows remain time-consuming, labor-intensive, and difficult to transfer. AuraLuxMuse encodes music and professional cue sequences into a shared retrieval space, estimates cue-event density, and retargets selected fixture commands to the destination stage. It assists pre-production authoring by returning editable cues rather than replacing the designer with an unconstrained generator. At the heart of AuraLuxMuse are two key modules: Lighting-Aligned Music Pretraining (LAMP), which performs contrastive learning between audio and lighting cues for alignment, and Preference-Adaptive Mixture of Experts (PAMoE), which conditions preference-aware cue retrieval and adaptation on designers' intent through a gated ensemble of style-specific expert networks. To support training and evaluation, we introduce Musilux, the first dataset of paired musical audio and professional lighting cue sequences under diverse performance scenarios. We evaluate AuraLuxMuse across both virtual simulation environments and professional-grade laboratories. Experimental results, including objective and subjective evaluation, demonstrate that AuraLuxMuse retrieves and adapts stage-lighting cues that are visually cohesive, semantically meaningful, and artistically expressive, showing its potential for AI-assisted aesthetic stage design.
| Comments: | Accepted to appear in SIGGRAPH Asia 2026 Conference Papers |
| Subjects: | Multimedia (cs.MM); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11792 [cs.MM] |
| (or arXiv:2610.11792v1 [cs.MM] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11792 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junyu Deng [view email]
[v1]
Thu, 8 Oct 2026 12:06:03 UTC (48,782 KB)
来源：arXiv：cs.AI · arxiv.org