Reading: GVCNN — One-For-All Group Variation Convolutional Neural Network (HEVC Inter)

Outperforms CNNIF & Zhang VCIP’17. 2.2% Average BD-Rate Reduction Under LDP.

Outline

1. Fractional Interpolation in HEVC

Positions of different fractional pixels

fh(·) and fq(·) represent the learned mapping between integer pixels and grouped variations of half- and quarter-pixel positions, respectively.

And GVCNN attempts to estimate the mapping function.

2. GVCNN: Network Architecture

GVCNN: Network Architecture

3. Training Data Generation

Training Data Generation

4. Experimental Results

BD-Rate (%) on HEVC Test Sequences
BD-Rate (%) on UHD Sequences
RD Curves for 3 Sequences
BD-Rate (%) on HEVC Test Sequences
GVCNN Separate Models
Blurring
Red: GVCNN, Blue: DCTIF
Hitting Ratios

This is the 30th story in this month!

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store