Abstract | ||
---|---|---|
Light-field cameras have now become available in both consumer and industrial applications, and recent papers have demonstrated practical algorithms for depth recovery from a passive single-shot capture. However, current light-field depth estimation methods are designed for Lambertian objects and fail or degrade for glossy or specular surfaces. Because light-field cameras have an array of micro-lenses, the captured data allows modification of both focus and perspective viewpoints. In this paper, we develop an iterative approach to use the benefits of light-field data to estimate and remove the specular component, improving the depth estimation. The approach enables light-field data depth estimation to support both specular and diffuse scenes. We present a physically-based method that estimates one or multiple light source colors. We show our method outperforms current state-of-the-art diffuse and specular separation and depth estimation algorithms in multiple real world scenarios. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-16181-5_41 | COMPUTER VISION - ECCV 2014 WORKSHOPS, PT II |
Keywords | Field | DocType |
Markov Random Fields,Depth Estimation,Color Constancy,Specular Surface,Specular Component | Color constancy,Computer vision,Computer science,Specular reflection,Light field,Artificial intelligence,Light source | Conference |
Volume | ISSN | Citations |
8926 | 0302-9743 | 7 |
PageRank | References | Authors |
0.52 | 17 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael W. Tao | 1 | 225 | 11.75 |
Ting-chun Wang | 2 | 440 | 28.49 |
Jitendra Malik | 3 | 39445 | 3782.10 |
Ravi Ramamoorthi | 4 | 4481 | 237.21 |