| Paper Abstract and Keywords |
| Presentation |
2025-02-18 11:25
Efficient Physics Informed Dynamic Neural Fluid Fields Reconstruction From Sparse Video
Yangcheng Xiang, Yoshinori Dobashi (Hokudai) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
Efficiently inferring the latent physical properties of fluids from sparse 2D videos has long been a challenging problem, particularly in scenarios involving complex lighting conditions and obstacles. Our research aims to reconstruct the neural density field and corresponding velocity field of fluids from sparse fluid videos by leveraging known physical priors, to get realistic fluid reconstruction results. Our method employs physics-based deep learning to train a continuous, time-sequential neural physical radiance field in an end-to-end manner. On one hand, we reduce the model scale and enhance training and rendering efficiency by directly training on multi-level grids. On the other hand, leveraging the differentiable nature of physical simulations, we introduce a global physical optimization layer to improve the physical consistency and realism of the reconstructed results. Additionally, the high compression ratio of neural radiance fields allows for efficient storage of dynamic fluid physical information. Our method exhibits physically accurate fluid reconstructions and efficient training times, providing new possibilities for fluid re-simulation, editing, future prediction, and neural dynamic scene composition. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Physics-Informed Deep Learning / Fluid Reconstruction / NeRF / / / / / |
| Reference Info. |
ITE Tech. Rep., vol. 49, no. 4, AIT2025-6, pp. 29-33, Feb. 2025. |
| Paper # |
AIT2025-6 |
| Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
ME AIT MMS IEICE-IE IEICE-ITS SIP |
| Conference Date |
2025-02-18 - 2025-02-19 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
Hokkaido Univ. |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
Image Processing, etc. |
| Paper Information |
| Registration To |
AIT |
| Conference Code |
2025-02-ME-AIT-MMS-IE-ITS-SIP |
| Language |
English |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
Efficient Physics Informed Dynamic Neural Fluid Fields Reconstruction From Sparse Video |
| Sub Title (in English) |
|
| Keyword(1) |
Physics-Informed Deep Learning |
| Keyword(2) |
Fluid Reconstruction |
| Keyword(3) |
NeRF |
| Keyword(4) |
|
| Keyword(5) |
|
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Yangcheng Xiang |
| 1st Author's Affiliation |
Hokkaido University (Hokudai) |
| 2nd Author's Name |
Yoshinori Dobashi |
| 2nd Author's Affiliation |
Hokkaido University (Hokudai) |
| 3rd Author's Name |
|
| 3rd Author's Affiliation |
() |
| 4th Author's Name |
|
| 4th Author's Affiliation |
() |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| 21st Author's Name |
|
| 21st Author's Affiliation |
() |
| 22nd Author's Name |
|
| 22nd Author's Affiliation |
() |
| 23rd Author's Name |
|
| 23rd Author's Affiliation |
() |
| 24th Author's Name |
|
| 24th Author's Affiliation |
() |
| 25th Author's Name |
|
| 25th Author's Affiliation |
() |
| 26th Author's Name |
/ / |
| 26th Author's Affiliation |
()
() |
| 27th Author's Name |
/ / |
| 27th Author's Affiliation |
()
() |
| 28th Author's Name |
/ / |
| 28th Author's Affiliation |
()
() |
| 29th Author's Name |
/ / |
| 29th Author's Affiliation |
()
() |
| 30th Author's Name |
/ / |
| 30th Author's Affiliation |
()
() |
| 31st Author's Name |
/ / |
| 31st Author's Affiliation |
()
() |
| 32nd Author's Name |
/ / |
| 32nd Author's Affiliation |
()
() |
| 33rd Author's Name |
/ / |
| 33rd Author's Affiliation |
()
() |
| 34th Author's Name |
/ / |
| 34th Author's Affiliation |
()
() |
| 35th Author's Name |
/ / |
| 35th Author's Affiliation |
()
() |
| 36th Author's Name |
/ / |
| 36th Author's Affiliation |
()
() |
| Speaker |
Author-1 |
| Date Time |
2025-02-18 11:25:00 |
| Presentation Time |
15 minutes |
| Registration for |
AIT |
| Paper # |
MMS2025-6, ME2025-6, AIT2025-6, SIP2025-6 |
| Volume (vol) |
vol.49 |
| Number (no) |
no.4 |
| Page |
pp.29-33 |
| #Pages |
5 |
| Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |