Physics-Informed Neural Fields with Neural Implicit Surface for Fluid Reconstruction

Simple item page
dc.contributor.authorDuan, Zhengen_US
dc.contributor.authorRen, Zhongen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:04:29Z
dc.date.available2024-10-13T18:04:29Z
dc.date.issued2024
dc.description.abstractRecovering fluid density and velocity from multi-view RGB videos poses a formidable challenge. Existing solutions typically assume knowledge of obstacles and lighting, or are designed for simple fluid scenes without obstacles or complex lighting. Addressing these challenges, our study presents a novel hybrid model named PINFS, which ingeniously fuses the capabilities of Physics-Informed Neural Fields (PINF) and Neural Implicit Surfaces (NeuS) to accurately reconstruct scenes containing smoke. By combining the capabilities of SIREN-NeRFt in PINF for creating realistic smoke representations and the accuracy of NeuS in depicting solid obstacles, PINFS excels in providing detailed reconstructions of smoke scenes with improved visual authenticity and physical precision. PINFS distinguishes itself by incorporating solid's view-independent opaque density and addressing Neumann boundary conditions through signed distances from NeuS. This results in a more realistic and physically plausible depiction of smoke behavior in dynamic scenarios. Comprehensive evaluations of synthetic and real-world datasets confirm the model's superior performance in complex scenes with obstacles. PINFS introduces a novel framework for realistically and physically consistent rendering of complex fluid dynamics scenarios, pushing the boundaries in the utilization of mixed physical and neural-based approaches. The code is available at https://github.com/zduan3/pinfs_code.en_US
dc.description.sectionheadersSimulation
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241298
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241298
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241298
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Scene understanding; Neural networks; Physical simulation
dc.subjectComputing methodologies → Scene understanding
dc.subjectNeural networks
dc.subjectPhysical simulation
dc.titlePhysics-Informed Neural Fields with Neural Implicit Surface for Fluid Reconstructionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241298.pdf
Size:
6.98 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters