Abstract | ||
---|---|---|
In this work, we propose a novel view-approximation oriented image database generation approach (VOIDGA) that enables the adequate generation of arbitrary views. Our approach utilizes Depth Image Based Rendering (DIBR) techniques to derive novel views based on a set of depth images. In contrast to approaches that store a huge amount of images to cover a wide range of possible view directions, VOIDGA identifies and stores only those images that significantly contribute to the overall view-approximation quality while bounding the resulting approximation error. This further reduces the size of image databases and the number of images that need to be processed by DIBR algorithms. We demonstrate VOIDGA on several challenging real-world examples, and compare our approximations against ground truth renderings using two image-based metrics. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/LDAV.2018.8739204 | 2018 IEEE 8th Symposium on Large Data Analysis and Visualization (LDAV) |
Keywords | Field | DocType |
Image Database,Depth Image Based Rendering,Geometry Reconstruction,View Approximation | Approximation algorithm,Computer vision,Computer science,Surface triangulation,Triangulation (social science),Pixel,Artificial intelligence,Rendering (computer graphics),Point cloud,Image-based modeling and rendering,Approximation error | Conference |
ISSN | ISBN | Citations |
2373-7514 | 978-1-5386-6874-0 | 1 |
PageRank | References | Authors |
0.35 | 22 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jonas Lukasczyk | 1 | 23 | 5.15 |
Eric Kinner | 2 | 1 | 0.35 |
James Ahrens | 3 | 233 | 35.07 |
Heike Leitte | 4 | 111 | 11.05 |
Christoph Garth | 5 | 751 | 50.85 |