Saved in:
Bibliographic Details
Main Author: Roy, Bruno
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.08188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929383222018048
author Roy, Bruno
author_facet Roy, Bruno
contents In this work, we introduce FluidsFormer: a transformer-based approach for fluid interpolation within a continuous-time framework. By combining the capabilities of PITT and a residual neural network (RNN), we analytically predict the physical properties of the fluid state. This enables us to interpolate substep frames between simulated keyframes, enhancing the temporal smoothness and sharpness of animations. We demonstrate promising results for smoke interpolation and conduct initial experiments on liquids.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08188
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Attention-Based Learning for Fluid State Interpolation and Editing in a Time-Continuous Framework
Roy, Bruno
Machine Learning
Graphics
In this work, we introduce FluidsFormer: a transformer-based approach for fluid interpolation within a continuous-time framework. By combining the capabilities of PITT and a residual neural network (RNN), we analytically predict the physical properties of the fluid state. This enables us to interpolate substep frames between simulated keyframes, enhancing the temporal smoothness and sharpness of animations. We demonstrate promising results for smoke interpolation and conduct initial experiments on liquids.
title Attention-Based Learning for Fluid State Interpolation and Editing in a Time-Continuous Framework
topic Machine Learning
Graphics
url https://arxiv.org/abs/2406.08188