Abstract
Light-field stereo
matching problems are commonly modeled by Markov Random Fields (MRFs)
for statistical inference of depth maps. Nevertheless, most previous
approaches did not adapt to image statistics but instead adopted fixed
model parameters. They explored explicit vision cues, such as depth
consistency and occlusion, to provide local adaptability and enhance
depth quality. However, such additional assumptions could end up
confining their applicability, e.g. algorithms designed for dense view
sampling are not suitable for sparse one. In this paper, we get back to
MRF fundamentals and develop an empirical Bayesian framework—Robust
Pseudo Random Field—to explore intrinsic statistical cues for broad
applicability. Based on pseudo-likelihoods with hidden soft-decision
priors, we apply soft expectation-maximization (EM) for good model
fitting and perform hard EM for robust depth estimation. We introduce
novel pixel difference models to enable such adaptability and robustness
simultaneously. Accordingly, we devise a stereo matching algorithm to
employ this framework on dense, sparse, and even denoised light fields.
It can be applied to both true-color and grey-scale pixels. Experimental
results show that it estimates scene-dependent parameters robustly and
converges quickly. In terms of depth accuracy and computation speed, it
also outperforms state-of-the-art algorithms constantly.
Publications
C.-T.
Huang, "Empirical Bayesian Light-Field Stereo Matching by Robust
Pseudo Random Field Modeling," IEEE
Transactions on Pattern Analysis and Machine Intelligence,
accepted.
[preprint
(24MB)] [appendices
(0.2MB)]
C.-T. Huang, "Robust
Pseudo Random Fields for Light-Field Stereo Matching," IEEE ICCV 2017
(oral presentation).
[preprint
(6MB)]
Software
Executable
program
-
[rprf_matlab2017a.zip (13MB)]:
Compiled by Visual Studio 2012 with MATLAB R2017a dynamic-link
library
Dataset
3x3 test
light fields converted from raw light-field data in
EPFL dataset by
Lytro Power Tools Beta
[dataset.zip (11MB)]
Supplementary Experimental
Results
- Results on Five Crosshair Views with
Grey-Scale Intensity [link]
- Results on 17x17 Light Fields [link]
|