Initial commit

y-zheng18 · Dec 19, 2023 · 255df1e · 255df1e
1 parent 4be88c6
commit 255df1e
Show file tree

Hide file tree

Showing 31 changed files with 6,943 additions and 35 deletions.
diff --git a/.gitignore b/.gitignore
@@ -20,6  20,7 @@ parts/
 sdist/
 var/
 wheels/
 pip-wheel-metadata/
 share/python-wheels/
 *.egg-info/
 .installed.cfg
@@ -49,7  50,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-cover/
 
 # Translations
 *.mo
@@ -72,7  72,6 @@ instance/
 docs/_build/
 
 # PyBuilder
-.pybuilder/
 target/
 
 # Jupyter Notebook
@@ -83,9  82,7 @@ profile_default/
 ipython_config.py
 
 # pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
 .python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
@@ -94,22  91,7 @@ ipython_config.py
 #   install all needed dependencies.
 #Pipfile.lock
 
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow
 __pypackages__/
 
 # Celery stuff
@@ -145,16  127,7 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
 .idea/
 .DS_Store
 
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
 logs/
diff --git a/README.md b/README.md
@@ -1,2  1,54 @@
-# HyFluid
-Official code for Inferring Hybrid Neural Fluid Fields from Videos (NeurIPS 2023) 
 # Inferring Hybrid Neural Fluid Fields from Videos
 This is the official code for Inferring Hybrid Neural Fluid Fields from Videos (NeurIPS 2023).
 
 ![teaser](assets/demo_hyfluid.gif)
 
 **[[Paper](https://arxiv.org/pdf/2312.06561.pdf)] [[Project Page](https://kovenyu.com/hyfluid/)]**
 
 ## Installation
 Install with conda:
 ```bash
 conda env create -f environment.yml
 conda activate hyfluid
 ```
 or with pip:
 ```bash
 pip install -r requirements.txt
 ```
 
 ## Data
 The demo data is available at [data/ScalarReal](data/ScalarReal). 
 The full ScalarFlow dataset can be downloaded [here](https://ge.in.tum.de/publications/2019-scalarflow-eckert/).
 
 ## Quick Start
 To learn the hybrid neural fluid fields from the demo data, firstly reconstruct the density field by running (~40min):
 ```bash
 bash scripts/train.sh
 ```
 Then, reconstruct the velocity field by jointly training with the density field (~15 hours on a single A6000 GPU.):
 ```bash
 bash scripts/train_j.sh
 ```
 Finally, add vortex particles and optimize their physical parameters (~40min):
 ```bash
 bash scripts/train_vort.sh
 ```
 The results will be saved in `./logs/exp_real`. With the learned hybrid neural fluid fields, you can re-simulate the fluid by using the velocity fields to advect density:
 ```bash
 bash scripts/test_resim.sh
 ```
 Or, you can predict the future states by extrapolating the velocity fields:
 ```bash
 bash scripts/test_future_pred.sh
 ```
 
 ## Citation
 If you find this code useful for your research, please cite our paper:
 ```
 @article{yu2023inferring,
   title={Inferring Hybrid Neural Fluid Fields from Videos},
   author={Yu, Hong-Xing and Zheng, Yang and Gao, Yuan and Deng, Yitong and Zhu, Bo and Wu, Jiajun},
   journal={NeurIPS},
   year={2023}
 }
 ```
diff --git a/assets/demo_hyfluid.gif b/assets/demo_hyfluid.gif
diff --git a/configs/scalarflowreal.txt b/configs/scalarflowreal.txt
@@ -0,0  1,8 @@
 expname = scalarflowreal
 basedir = ./logs
 datadir = ./data/ScalarReal
 
 N_samples = 192
 N_rand = 1024
 
 half_res = True
diff --git a/data/ScalarReal/info.json b/data/ScalarReal/info.json
@@ -0,0  1,231 @@
 {
     "train_videos": [
         {
             "file_name": "train00.mp4",
             "frame_rate": 30,
             "frame_num": 120,
             "camera_angle_x": 0.40746459248665245,
             "camera_hw": [
                 1920,
                 1080
             ],
             "transform_matrix": [
                 [
                     0.48627835512161255,
                     -0.24310240149497986,
                     -0.8393059968948364,
                     -0.7697111964225769
                 ],
                 [
                     -0.01889985240995884,
                     0.9573688507080078,
                     -0.2882491946220398,
                     0.013170702382922173
                 ],
                 [
                     0.8735995292663574,
                     0.15603208541870117,
                     0.4609531760215759,
                     0.3249526023864746
                 ],
                 [
                     0.0,
                     0.0,
                     0.0,
                     1.0
                 ]
             ]
         },
         {
             "file_name": "train01.mp4",
             "frame_rate": 30,
             "frame_num": 120,
             "camera_angle_x": 0.39413608028840563,
             "camera_hw": [
                 1920,
                 1080
             ],
             "transform_matrix": [
                 [
                     0.8157652020454407,
                     -0.1372431218624115,
                     -0.5618642568588257,
                     -0.39192497730255127
                 ],
                 [
                     -0.04113851860165596,
                     0.9552109837532043,
                     -0.2930521070957184,
                     0.010452679358422756
                 ],
                 [
                     0.5769183039665222,
                     0.262175977230072,
                     0.7735819220542908,
                     0.8086869120597839
                 ],
                 [
                     0.0,
                     0.0,
                     0.0,
                     1.0
                 ]
             ]
         },
         {
             "file_name": "train03.mp4",
             "frame_rate": 30,
             "frame_num": 120,
             "camera_angle_x": 0.41320072172607875,
             "camera_hw": [
                 1920,
                 1080
             ],
             "transform_matrix": [
                 [
                     0.8836436867713928,
                     0.15215487778186798,
                     0.44274458289146423,
                     0.8974969983100891
                 ],
                 [
                     -0.021659603342413902,
                     0.9579861760139465,
                     -0.28599533438682556,
                     0.02680988796055317
                 ],
                 [
                     -0.46765878796577454,
                     0.24312829971313477,
                     0.8498140573501587,
                     0.8316138386726379
                 ],
                 [
                     0.0,
                     0.0,
                     0.0,
                     1.0
                 ]
             ]
         },
         {
             "file_name": "train04.mp4",
             "frame_rate": 30,
             "frame_num": 120,
             "camera_angle_x": 0.40746459248665245,
             "camera_hw": [
                 1920,
                 1080
             ],
             "transform_matrix": [
                 [
                     0.6336104273796082,
                     0.20118704438209534,
                     0.7470352053642273,
                     1.2956339120864868
                 ],
                 [
                     0.014488859102129936,
                     0.9623404741287231,
                     -0.27146074175834656,
                     0.02436656318604946
                 ],
                 [
                     -0.7735165357589722,
                     0.1828240603208542,
                     0.6068339943885803,
                     0.497546911239624
                 ],
                 [
                     0.0,
                     0.0,
                     0.0,
                     1.0
                 ]
             ]
         }
     ],
     "test_videos": [
         {
             "file_name": "train02.mp4",
             "frame_rate": 30,
             "frame_num": 120,
             "camera_angle_x": 0.41505697544547304,
             "camera_hw": [
                 1920,
                 1080
             ],
             "transform_matrix": [
                 [
                     0.999511182308197,
                     -0.0030406631994992495,
                     -0.03111351653933525,
                     0.2844361364841461
                 ],
                 [
                     -0.005995774641633034,
                     0.9581364989280701,
                     -0.2862490713596344,
                     0.011681094765663147
                 ],
                 [
                     0.03068138100206852,
                     0.28629571199417114,
                     0.9576499462127686,
                     0.9857829809188843
                 ],
                 [
                     0.0,
                     0.0,
                     0.0,
                     1.0
                 ]
             ]
         }
     ],
     "frame_bkg_color": [
         0.0,
         0.0,
         0.0
     ],
     "voxel_scale": [
         0.4909,
         0.73635,
         0.4909
     ],
     "voxel_matrix": [
         [
             7.549790126404332e-08,
             0.0,
             1.0,
             0.081816665828228
         ],
         [
             0.0,
             1.0,
             0.0,
             -0.044627271592617035
         ],
         [
             -1.0,
             0.0,
             7.549790126404332e-08,
             -0.004908999893814325
         ],
         [
             0.0,
             0.0,
             0.0,
             1.0
         ]
     ],
     "render_center":[
         0.3382070094283088, 
         0.38795384153014023, 
         -0.2609209839653898
     ],
     "near":1.1,
     "far":1.5,
     "phi":20.0,
     "rot":"Y"
 }
diff --git a/data/ScalarReal/train00.mp4 b/data/ScalarReal/train00.mp4
diff --git a/data/ScalarReal/train01.mp4 b/data/ScalarReal/train01.mp4
diff --git a/data/ScalarReal/train02.mp4 b/data/ScalarReal/train02.mp4
diff --git a/data/ScalarReal/train03.mp4 b/data/ScalarReal/train03.mp4
diff --git a/data/ScalarReal/train04.mp4 b/data/ScalarReal/train04.mp4