MoCA通过组件路由与压缩，实现可扩展的3D组合生成。
MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
- 按重要性选择关键组件，稀疏化全局注意力
- 未选组件保留上下文先验，降低计算开销
- 支持大量组件的精细3D资产生成，适合设计场景
组合性对3D物体与场景生成至关重要，但现有部件感知的3D生成方法因组件增多导致全局注意力呈二次增长，难以扩展。本文提出MoCA，包含两项核心设计：(1) 基于重要性的组件路由，仅对前k个相关组件进行稀疏全局注意力；(2) 无关组件压缩，在保留上下文先验的同时降低全局注意力的计算复杂度。该设计使MoCA在保持高生成质量的前提下，实现可扩展的细粒度3D组合资产创建。大量实验表明，MoCA在组合物体与场景生成任务上均优于基线模型。
原文摘要 · Abstract (English)
Compositionality is critical for 3D object and scene generation, but existing part-aware 3D generation methods suffer from poor scalability due to quadratic global attention costs when increasing the number of components. In this work, we present MoCA, a compositional 3D generative model with two key designs: (1) importance-based component routing that selects top-k relevant components for sparse global attention, and (2) unimportant components compression that preserve contextual priors of unselected components while reducing computational complexity of global attention. With these designs, MoCA enables efficient, fine-grained compositional 3D asset creation with scalable number of components. Extensive experiments show MoCA outperforms baselines on both compositional object and scene generation tasks. Project page: https://lizhiqi49.github.io/MoCA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。