コンピューターグラフィックスの新たなAIベンチマークに到達(Researchers Reach New AI Benchmark for Computer Graphics)

ad

2024-03-05 ジョージア工科大学

Bo Zhuらの研究チームは、AIニューラルネットワークの進化により、コンピュータグラフィックスシミュレーションが自然現象をより正確に表現できることを示しました。彼らは機械学習モデルを使用し、既知の現象の高度なシミュレーションを作成し、その新しいベンチマークが未知の現象の表現にも道を開く可能性があると述べました。

<関連情報>

ニューラル・フロー・マップによる流体シミュレーション
Fluid Simulation on Neural Flow Maps

Yitong Deng, Hong-Xing Yu, Diyang Zhang, Jiajun Wu, Bo Zhu
arXiv  Submitted on 22 Dec 2023
DOI:https://doi.org/10.1145/3618392

コンピューターグラフィックスの新たなAIベンチマークに到達(Researchers Reach New AI Benchmark for Computer Graphics)

We introduce Neural Flow Maps, a novel simulation method bridging the emerging paradigm of implicit neural representations with fluid simulation based on the theory of flow maps, to achieve state-of-the-art simulation of inviscid fluid phenomena. We devise a novel hybrid neural field representation, Spatially Sparse Neural Fields (SSNF), which fuses small neural networks with a pyramid of overlapping, multi-resolution, and spatially sparse grids, to compactly represent long-term spatiotemporal velocity fields at high accuracy. With this neural velocity buffer in hand, we compute long-term, bidirectional flow maps and their Jacobians in a mechanistically symmetric manner, to facilitate drastic accuracy improvement over existing solutions. These long-range, bidirectional flow maps enable high advection accuracy with low dissipation, which in turn facilitates high-fidelity incompressible flow simulations that manifest intricate vortical structures. We demonstrate the efficacy of our neural fluid simulation in a variety of challenging simulation scenarios, including leapfrogging vortices, colliding vortices, vortex reconnections, as well as vortex generation from moving obstacles and density differences. Our examples show increased performance over existing methods in terms of energy conservation, visual complexity, adherence to experimental observations, and preservation of detailed vortical structures.

1702地球物理及び地球化学
ad
ad
Follow
ad
タイトルとURLをコピーしました