These publications are provided on the
LIVE website for research purposes ONLY. No part of these documents
may be distributed for commercial purposes
SSIM based range image quality assessment
W. Malpica and A.C. Bovik
Fourth International orkshop on Video Processing and Quality Metrics for Consumer Electronics
Abstract
Although image quality assessment (IQA) has observed
much research and advancement in the past, not much
progress has been made towards the development of quality
assessment metrics for range images. The current metrics
being used to assess the quality of range images are reminiscent
to the old IQA metrics such as mean squared error
that have since been replaced with metrics which better correlate
with human perception. This paper presents two new
algorithms for range image quality assessment (RIQA). The
first, R-SSIM, is based off the Multi-Scale Structural Similarity
Index (MS-SSIM), while the other is an extension of
the Complex Wavelet SSIM (CW-SSIM) metric for use in
RIQA. The utility of these metrics is demonstrated through
a re-evaluation of Scharstein and Szeliski’s online evaluation
of dense two-frame stereo correspondence algorithms.
[Download PDF]
