提出MeshRipple，实现拓扑连贯的3D网格自回归生成。
MeshRipple: Structured Autoregressive Generation of Artist-Meshes
- 按表面拓扑顺序生成，从前沿向外扩展
- 生成完整无洞网格，优于现有基线模型
- 适合需要高质量3D网格的生成任务
网格是3D资产的主要表示形式。自回归网格生成器将面片序列化，并通过滑动窗口推理训练以应对内存限制，但这种处理方式破坏了长程几何依赖，导致出现孔洞和碎片化组件。为解决这一关键问题，我们提出MeshRipple，其通过从活跃生成前沿向外扩展，类似水面上的涟漪。MeshRipple基于三项核心创新：面向前沿的广度优先搜索（BFS）标记方法，使生成顺序与表面拓扑对齐；扩展式预测策略，确保表面生长连贯且完整；以及稀疏注意力全局记忆机制，提供近乎无限的感受野以解决长程拓扑依赖。该集成设计使MeshRipple能够生成具有高表面保真度和拓扑完整性的网格，显著超越近期强基线模型。
原文摘要 · Abstract (English)
Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines.
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。