Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization

arXiv:2308.02494v3 Announce Type: replace-cross
Abstract: 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 …

arxiv cs.cv cs.gr data data visualization eess.iv grid networks representation scale type visualization