用于大规模数据可视化的自适应放置多网格场景表示网络
Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization
AI总结：
针对大规模科学体数据，本文提出自适应放置多网格 SRN（APMGSRN）与多 GPU 域分解训练推理方法，提升重建精度并支持实时神经体绘制。
摘要：
场景表示网络（SRN）最近被提出用于科学数据的压缩与可视化。然而，最先进的 SRN 不会根据科学数据中发现的复杂特征调整可用网络参数的分配，从而导致重建质量下降。我们通过一种自适应放置的多网格 SRN（APMGSRN）解决这一缺陷，并提出一种域分解训练与推理技术，用于在多 GPU 系统上加速并行训练。我们还发布了一个开源神经体绘制应用程序，允许与任何基于 PyTorch 的 SRN 进行即插即用式渲染。我们提出的 APMGSRN 架构使用多个空间自适应特征网格，这些网格学习在域内的放置位置，以便在体数据中误差较高的位置动态分配更多神经网络资源，从而提升 SRN 对科学数据的最先进重建精度，同时无需像以往自适应模型那样进行昂贵的八叉树细化、剪枝和遍历。在用于表示大规模数据的域分解方法中，我们在体数据的不同分块上并行训练一组 APMGSRN，以减少训练时间，同时避免为无法装入 GPU 显存的过大体数据采用核外解决方案所必需的开销。训练完成后，轻量级 SRN 被用于我们开源渲染器中的实时神经体绘制，在其中可以探索任意视角和传递函数。本文副本、全部代码、实验中使用的所有模型，以及所有补充材料和视频均可在 https://github.com/skywolf829/APMGSRN 获取。
英文摘要：
Scene representation networks (SRNs) have been recently proposed for compression and visualization of scientific data. However, state-of-the-art SRNs do not adapt the allocation of available network parameters to the complex features found in scientific data, leading to a loss in reconstruction quality. We address this shortcoming with an adaptively placed multi-grid SRN (APMGSRN) and propose a domain decomposition training and inference technique for accelerated parallel training on multi-GPU systems. We also release an open-source neural volume rendering application that allows plug-and-play rendering with any PyTorch-based SRN. Our proposed APMGSRN architecture uses multiple spatially adaptive feature grids that learn where to be placed within the domain to dynamically allocate more neural network resources where error is high in the volume, improving state-of-the-art reconstruction accuracy of SRNs for scientific data without requiring expensive octree refining, pruning, and traversal like previous adaptive models. In our domain decomposition approach for representing large-scale data, we train an set of APMGSRNs in parallel on separate bricks of the volume to reduce training time while avoiding overhead necessary for an out-of-core solution for volumes too large to fit in GPU memory. After training, the lightweight SRNs are used for realtime neural volume rendering in our open-source renderer, where arbitrary view angles and transfer functions can be explored. A copy of this paper, all code, all models used in our experiments, and all supplemental materials and videos are available at https://github.com/skywolf829/APMGSRN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
