发表机构
Fudan University; Shanghai Theatre Academy; Nanjing University of the Arts（复旦大学; 上海戏剧学院; 南京艺术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AuraLuxMuse是集成专家知识、表征学习与偏好自适应建模的自动化舞台灯光设计系统，含LAMP与PAMoE模块，依托Musilux数据集，可生成具艺术表现力的可编辑灯光cue，助力AI辅助美学舞台设计。
AI 中文摘要
我们提出AuraLuxMuse，这是一款集成专家知识、表征学习与偏好自适应建模的新型自动化美学舞台灯光设计系统。现场演出的灯光设计需将音乐特征无缝转化为动态灯光行为，但传统工作流程耗时、费力且难以迁移。AuraLuxMuse将音乐与专业 cue 序列编码至共享检索空间，估计 cue-事件密度，并将选定的灯具指令重定向至目标舞台；它通过返回可编辑 cue 辅助前期制作创作，而非用无约束生成器取代设计师。AuraLuxMuse的核心是两个关键模块：灯光对齐音乐预训练（LAMP），该模块对音频与灯光 cue 执行对比学习以实现对齐；偏好自适应混合专家（PAMoE），该模块通过风格特定专家网络的门控集成，基于设计师意图实现感知偏好的 cue 检索与适配。为支持训练与评估，我们推出Musilux——首个涵盖多样演出场景的配对音乐音频与专业灯光 cue 序列数据集。我们在虚拟仿真环境与专业级实验室中对AuraLuxMuse进行评估，包含客观与主观评估的实验结果表明，AuraLuxMuse检索并适配的舞台灯光 cue 视觉连贯、语义明确且具艺术表现力，展现了其在AI辅助美学舞台设计领域的潜力。
英文摘要
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.
CommentsAccepted to appear in SIGGRAPH Asia 2026 Conference Papers
