Information Technology Reference
In-Depth Information
Chapter 10
Spatiotemporal Video Upscaling Using
Motion-Assisted Steering Kernel (MASK)
Regression
Hiroyuki Takeda, Peter van Beek, and Peyman Milanfar
Abstract. In this chapter, we present Motion Assisted Steering Kernel (MASK) re-
gression, a novel multi-frame approach for interpolating video data spatially, tem-
porally, or spatiotemporally, and for video noise reduction, including compression
artifact removal. The MASK method takes both local spatial orientations and local
motion vectors into account and adaptively constructs a suitable filter at every posi-
tion of interest. Moreover, we present a practical algorithm based on MASK that is
both robust and computationally efficient. In order to reduce the computational and
memory requirements, we process each frame in a block-by-block manner, utilizing
a block-based motion model. Instead of estimating the local dominant orientation
by singular value decomposition, we estimate the orientations based on a technique
similar to vector quantization. We develop a technique to locally adapt the regression
order, which allows enhancing the denoising effect in flat areas, while effectively
preserving major edges and detail in texture areas. Comparisons between MASK
and other state-of-the-art video upscaling methods demonstrate the effectiveness of
our approach.
1
Introduction
Advances in video display technology have increased the need for high-quality and
robust video interpolation and artifact removal methods. In particular, LCD flat-
panel displays are currently being developed with very high spatial resolution and
very high frame rates. For example, so-called “4K” resolution panels are capable
of displaying 2160
×
4096 full color pixels. Also, LCD panels with frame rates of
·
Search WWH ::




Custom Search