Adaptive multiresolution exemplar-based texture synthesis on animated fluids

We propose an approach to synthesize textures for the animated free surfaces of fluids. Because fluids deform and experience topological changes, it is challenging to maintain fidelity to a reference texture exemplar while avoiding visual artifacts such as distortion and discontinuities. We introduce an adaptive multiresolution synthesis approach that balances fidelity to the exemplar and consistency with the fluid motion. Given a 2D exemplar texture, an orientation field from the first frame, an animated velocity field, and polygonal meshes corresponding to the animated liquid, our approach advects the texture and the orientation field across frames, yielding a coherent sequence of textures conforming to the per-frame geometry. Our adaptiveness relies on local 2D and 3D distortion measures, which guide multiresolution decisions to resynthesize or preserve the advected content. We prevent popping artifacts by enforcing gradual changes in color over time. Our approach works well both on slow-moving liquids and on turbulent ones with splashes. In addition, we demonstrate good performance on a variety of stationary texture exemplars. • Adaptive multiresolution texture synthesis for animated fluid surfaces. • Multiresolution pyramids provide consistency to the animation and to the exemplar. • Local distortion detection by evaluating 2D and 3D stretching measures. • Popping prevention mechanism reduces abrupt changes in color during animation.

Authors

Institutions

Publication Details

Journal
Computers & Graphics
Published
2025-12-03
DOI
https://doi.org/10.1016/j.cag.2025.104490
Citations
1
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
article
Field-Weighted Citation Impact
1.28
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Adaptive multiresolution exemplar-based texture synthesis on animated fluids

David Mould, Julián E. Guzmán, Eric Paquette
1 citations
Computers & Graphics
Generative Adversarial Networks and Image Synthesis
1.28
article

Adaptive multiresolution exemplar-based texture synthesis on animated fluids

David Mould, Julián E. Guzmán, Eric Paquette
article en
1 citations

Abstract

We propose an approach to synthesize textures for the animated free surfaces of fluids. Because fluids deform and experience topological changes, it is challenging to maintain fidelity to a reference texture exemplar while avoiding visual artifacts such as distortion and discontinuities. We introduce an adaptive multiresolution synthesis approach that balances fidelity to the exemplar and consistency with the fluid motion. Given a 2D exemplar texture, an orientation field from the first frame, an animated velocity field, and polygonal meshes corresponding to the animated liquid, our approach advects the texture and the orientation field across frames, yielding a coherent sequence of textures conforming to the per-frame geometry. Our adaptiveness relies on local 2D and 3D distortion measures, which guide multiresolution decisions to resynthesize or preserve the advected content. We prevent popping artifacts by enforcing gradual changes in color over time. Our approach works well both on slow-moving liquids and on turbulent ones with splashes. In addition, we demonstrate good performance on a variety of stationary texture exemplars. • Adaptive multiresolution texture synthesis for animated fluid surfaces. • Multiresolution pyramids provide consistency to the animation and to the exemplar. • Local distortion detection by evaluating 2D and 3D stretching measures. • Popping prevention mechanism reduces abrupt changes in color during animation.

Computers & GraphicsVol. 134
Carleton University (CA), École de Technologie Supérieure (CA)
Openalex Percentile: Top 14%
Generative Adversarial Networks and Image Synthesis
1.28
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.