1 code implementation • 1 May 2020 • Chiyu Max Jiang, Soheil Esmaeilzadeh, Kamyar Azizzadenesheli, Karthik Kashinath, Mustafa Mustafa, Hamdi A. Tchelepi, Philip Marcus, Prabhat, Anima Anandkumar
We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs.
no code implementations • ICLR Workshop DeepDiffEq 2019 • Chiyu "Max" Jiang, Karthik Kashinath, Prabhat, Philip Marcus
To this end, we propose the use of a novel differentiable spectral projection layer for neural networks that efficiently enforces spatial PDE constraints using spectral methods, yet is fully differentiable, allowing for its use as a layer within Convolutional Neural Networks (CNNs) during end-to-end training.
1 code implementation • ICLR 2020 • Chiyu "Max" Jiang, Karthik Kashinath, Prabhat, Philip Marcus
To this end, we propose the use of a novel differentiable spectral projection layer for neural networks that efficiently enforces spatial PDE constraints using spectral methods, yet is fully differentiable, allowing for its use as a layer in neural networks that supports end-to-end training.
1 code implementation • ICCV 2019 • Chiyu "Max" Jiang, Dana Lynn Ona Lansigan, Philip Marcus, Matthias Nießner
We present a Deep Differentiable Simplex Layer (DDSL) for neural networks for geometric deep learning.
2 code implementations • ICLR 2019 • Chiyu "Max" Jiang, Dequan Wang, Jingwei Huang, Philip Marcus, Matthias Nießner
It has been challenging to analyze signals with mixed topologies (for example, point cloud with surface mesh).
1 code implementation • ICLR 2019 • Chiyu "Max" Jiang, Jingwei Huang, Karthik Kashinath, Prabhat, Philip Marcus, Matthias Niessner
We present an efficient convolution kernel for Convolutional Neural Networks (CNNs) on unstructured grids using parameterized differential operators while focusing on spherical signals such as panorama images or planetary signals.
Ranked #24 on Semantic Segmentation on Stanford2D3D Panoramic
no code implementations • 22 Sep 2017 • Chiyu "Max" Jiang, Philip Marcus
Automatic mesh-based shape generation is of great interest across a wide range of disciplines, from industrial design to gaming, computer graphics and various other forms of digital art.