Date: | October 8, 2015 |
---|---|
Location: | DC 1331 |
Time: | 11:30 |
Chair: | Christopher Batty |
Date: | October 15, 2015 | October 22, 2015 | October 29, 2015 | November 5, 2015 |
---|---|---|---|---|
Location: | DC 1331 11:30 | DC 1331 11:30 | DC 1331 11:30 | DC 1331 11:30 |
Chair: | Bill Cowan |
Ryan Goldade |
Craig Kaplan |
Marta Kryven |
Technical Presentation: | Christopher Batty |
Bill Cowan |
Ryan Goldade |
Craig Kaplan |
Yipeng Wang |
Title : Fluid Volume Modeling from Sparse Multi-view Images by Appearance Transfer
Abstract: The authors 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, the new method preserves the appearance of novel viewing angles by transferring the appearance information from input images to novel viewing angles. For appearance information, the authors use histograms of image intensities and steerable coefficients. They formulate the volume modeling as an energy minimization problem with statistical hard constraints, which is solved using an expectation maximization (EM)-like iterative algorithm. |
---|
Also see other Math and CS postings.