tempoGAN: a temporally coherent, volumetric GAN for super-resolution fluid flow




  • Paper topic: Animation and Simulation
  • Software type: Code
  • Able to run a replicability test: True
  • Replicability score: 5
  • Software language: C/C++, Python
  • License: Apache License 2.0
  • Build mechanism: CMakeLists, Not applicable (python, Matlab..)
  • Dependencies: CUDA / cudnn / tensorflow-gpu / imagio / keras / scipy / numpy / mantaflow
  • Documentation score {0,1,2}: 1
  • Reviewer: David Coeurjolly <david.coeurjolly@liris.cnrs.fr>
  • Time spent for the test (build->first run, timeout at 100min): 60min

Source code information


Complex CUDA/cudNN/tensorflow/manta infrastructure but well documented. Training data can be reproduced and pre-trained model can be easily reused.

If you want to contribute with another review, please follow these instructions.

Please consider to cut/paste/edit the raw JSON data attached to this paper.