Fluid volume modeling from sparse multi-view images by appearance transfer

Makoto Okabe, Yoshinori Dobashi, Ken Anjyo, Rikio Onai

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

We propose a method of three-dimensional (3D) modeling of volumetric fluid phenomena from sparse multi-view images (e.g., only a single-view input or a pair of front- and side-view inputs). The volume determined from such sparse inputs using previous methods appears blurry and unnatural with novel views; however, our method preserves the appearance of novel viewing angles by transferring the appearance information from input images to novel viewing angles. For appearance information, we use histograms of image intensities and steerable coefficients. We formulate the volume modeling as an energy minimization problem with statistical hard constraints, which is solved using an expectation maximization (EM)-like iterative algorithm. Our algorithm begins with a rough estimate of the initial volume modeled from the input images, followed by an iterative process whereby we first render the images of the current volume with novel viewing angles. Then, we modify the rendered images by transferring the appearance information from the input images, and we thereafter model the improved volume based on the modified images. We iterate these operations until the volume converges. We demonstrate our method successfully provides natural-looking volume sequences of fluids (i.e., fire, smoke, explosions, and a water splash) from sparse multiview videos. To create production-ready fluid animations, we further propose a method of rendering and editing fluids using a commercially available fluid simulator.

Original languageEnglish
Article number93
JournalACM Transactions on Graphics
Volume34
Issue number4
DOIs
Publication statusPublished - 2015 Jul 27
Externally publishedYes

Fingerprint

Fluids
Information use
Animation
Smoke
Explosions
Fires
Simulators
Water

Keywords

  • Image-based modeling
  • Natural phenomena animation
  • Single-view modeling
  • Texture analysis/synthesis
  • Volume modeling

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

Fluid volume modeling from sparse multi-view images by appearance transfer. / Okabe, Makoto; Dobashi, Yoshinori; Anjyo, Ken; Onai, Rikio.

In: ACM Transactions on Graphics, Vol. 34, No. 4, 93, 27.07.2015.

Research output: Contribution to journalArticle

Okabe, Makoto ; Dobashi, Yoshinori ; Anjyo, Ken ; Onai, Rikio. / Fluid volume modeling from sparse multi-view images by appearance transfer. In: ACM Transactions on Graphics. 2015 ; Vol. 34, No. 4.
@article{5e5f0e034d2b4a4d8c9ec824c689663a,
title = "Fluid volume modeling from sparse multi-view images by appearance transfer",
abstract = "We propose a method of three-dimensional (3D) modeling of volumetric fluid phenomena from sparse multi-view images (e.g., only a single-view input or a pair of front- and side-view inputs). The volume determined from such sparse inputs using previous methods appears blurry and unnatural with novel views; however, our method preserves the appearance of novel viewing angles by transferring the appearance information from input images to novel viewing angles. For appearance information, we use histograms of image intensities and steerable coefficients. We formulate the volume modeling as an energy minimization problem with statistical hard constraints, which is solved using an expectation maximization (EM)-like iterative algorithm. Our algorithm begins with a rough estimate of the initial volume modeled from the input images, followed by an iterative process whereby we first render the images of the current volume with novel viewing angles. Then, we modify the rendered images by transferring the appearance information from the input images, and we thereafter model the improved volume based on the modified images. We iterate these operations until the volume converges. We demonstrate our method successfully provides natural-looking volume sequences of fluids (i.e., fire, smoke, explosions, and a water splash) from sparse multiview videos. To create production-ready fluid animations, we further propose a method of rendering and editing fluids using a commercially available fluid simulator.",
keywords = "Image-based modeling, Natural phenomena animation, Single-view modeling, Texture analysis/synthesis, Volume modeling",
author = "Makoto Okabe and Yoshinori Dobashi and Ken Anjyo and Rikio Onai",
year = "2015",
month = "7",
day = "27",
doi = "10.1145/2766958",
language = "English",
volume = "34",
journal = "ACM Transactions on Graphics",
issn = "0730-0301",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - Fluid volume modeling from sparse multi-view images by appearance transfer

AU - Okabe, Makoto

AU - Dobashi, Yoshinori

AU - Anjyo, Ken

AU - Onai, Rikio

PY - 2015/7/27

Y1 - 2015/7/27

N2 - We propose a method of three-dimensional (3D) modeling of volumetric fluid phenomena from sparse multi-view images (e.g., only a single-view input or a pair of front- and side-view inputs). The volume determined from such sparse inputs using previous methods appears blurry and unnatural with novel views; however, our method preserves the appearance of novel viewing angles by transferring the appearance information from input images to novel viewing angles. For appearance information, we use histograms of image intensities and steerable coefficients. We formulate the volume modeling as an energy minimization problem with statistical hard constraints, which is solved using an expectation maximization (EM)-like iterative algorithm. Our algorithm begins with a rough estimate of the initial volume modeled from the input images, followed by an iterative process whereby we first render the images of the current volume with novel viewing angles. Then, we modify the rendered images by transferring the appearance information from the input images, and we thereafter model the improved volume based on the modified images. We iterate these operations until the volume converges. We demonstrate our method successfully provides natural-looking volume sequences of fluids (i.e., fire, smoke, explosions, and a water splash) from sparse multiview videos. To create production-ready fluid animations, we further propose a method of rendering and editing fluids using a commercially available fluid simulator.

AB - We propose a method of three-dimensional (3D) modeling of volumetric fluid phenomena from sparse multi-view images (e.g., only a single-view input or a pair of front- and side-view inputs). The volume determined from such sparse inputs using previous methods appears blurry and unnatural with novel views; however, our method preserves the appearance of novel viewing angles by transferring the appearance information from input images to novel viewing angles. For appearance information, we use histograms of image intensities and steerable coefficients. We formulate the volume modeling as an energy minimization problem with statistical hard constraints, which is solved using an expectation maximization (EM)-like iterative algorithm. Our algorithm begins with a rough estimate of the initial volume modeled from the input images, followed by an iterative process whereby we first render the images of the current volume with novel viewing angles. Then, we modify the rendered images by transferring the appearance information from the input images, and we thereafter model the improved volume based on the modified images. We iterate these operations until the volume converges. We demonstrate our method successfully provides natural-looking volume sequences of fluids (i.e., fire, smoke, explosions, and a water splash) from sparse multiview videos. To create production-ready fluid animations, we further propose a method of rendering and editing fluids using a commercially available fluid simulator.

KW - Image-based modeling

KW - Natural phenomena animation

KW - Single-view modeling

KW - Texture analysis/synthesis

KW - Volume modeling

UR - http://www.scopus.com/inward/record.url?scp=84947232633&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947232633&partnerID=8YFLogxK

U2 - 10.1145/2766958

DO - 10.1145/2766958

M3 - Article

VL - 34

JO - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

SN - 0730-0301

IS - 4

M1 - 93

ER -