Curated list for ML in FM

Aircraft design optimization made fast through modern automatic differentiation. Composable analysis tools for aerodynamics, propulsion, structures, trajectory design, and much more.

Unifying Flow, Stereo and Depth Estimation

3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

PIV image processing solver using LiteFlowNet model, written in PyTorch as the deep learning framework

PyTorch 1.2 implementation of IM-NET.

HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.

Generative Adversarial Networks and Autoencoders for 3D Shapes

Pytorch implementation of the PIV-LiteFlowNet-en (https://github.com/shengzesnail/PIV-LiteFlowNet-en)

Branch Gen3 is the current version. Codes for generating synthetic particle images for multi-camera systems, configured for use for PyPTV

Learning Optical Flow from a Few Matches (CVPR 2021)

PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design

The improved code for paper "Learning Implicit Fields for Generative Shape Modeling".

Unsupervised learning of Particle Image Velocimetry. (ISC 2020)

piv-image-generator: An image generating software package for planar PIV and Optical Flow benchmarking. To cite this software publication: https://www.sciencedirect.com/science/article/pii/S2352711…

Common functions for augmenting data to train deep optical flow models in PyTorch.