学习型局部网格细化
Learned Localized Mesh Refinement
浏览论文内容
中文总结 AI 辅助
本文提出一种基于自回归模型的局部条件网格细化方法,通过新颖标记器生成有效上采样轨迹,实现对输入网格选定区域的拓扑与几何自适应细化,并支持视图相关、物理感知等区域选择性控制。
中文摘要 AI 辅助
我们提出了一种用于自适应三角网格细化的神经方法,其中自回归模型向输入网格的选定区域添加几何细节,同时保持其余部分不变,这是高效分配网格预算的关键能力。现有的上采样方法难以实现这一点。经典细分方案在细化三角剖分时缺乏对底层形状的语义感知,也无法恢复粗输入中缺失的几何细节。最近的神经网格模型全局生成形状,牺牲了区域特定的控制。我们提出了一种新颖的标记器,可从单个网格产生组合上许多有效的上采样轨迹。在此类数据上训练后,我们的局部条件自回归架构允许直接操作输入网格目标区域内的拓扑和几何。我们针对最先进的方法验证了我们的方法,并展示了其执行具有区域选择性控制的自适应上采样的能力,这是现有方法所不具备的能力。这解锁了推理时的视图相关细化、物理感知区域细化以及以粗形状为条件的新网格合成。我们在以下网址提供代码:https URL。
英文摘要
We present a neural method for adaptive triangle mesh refinement, in which an autoregressive model adds geometric detail to selected regions of an input mesh while leaving the rest unchanged, a key capability for efficiently allocating mesh budget. Existing upsampling methods struggle to achieve this. Classical subdivision schemes refine triangulation without semantic awareness of the underlying shape or the ability to recover geometric details missing from a coarse input. Recent neural mesh models generate shapes globally, sacrificing region-specific control. We propose a novel tokenizer that yields combinatorially many valid upsampling trajectories from a single mesh. Trained on such data, our locally-conditioned autoregressive architecture allows for direct manipulation of topology and geometry within target regions of an input mesh. We validate our method against state-of-the-art approaches and demonstrate its ability to perform adaptive upsampling with region-selective control, a capability absent from existing approaches. This unlocks inference-time view-dependent refinement, physics-aware region refinement, and coarse-shape conditioned novel mesh synthesis. We provide code at https://github.com/seanxzhan/learned-localized-mesh-refinement/.
发表机构
- Massachusetts Institute of Technology (MIT)(麻省理工学院)
- Roblox(罗布乐思)
- Stanford(斯坦福大学)
机构由 AI 辅助整理,请以论文原文为准。