Propagation of quantization error in performing intra-prediction with deep learning

Raz Birman; Yoram Segal; Avishay David-Malka; Ofer Hadar; Ron Shmueli

doi:10.1117/12.2530341

6 September 2019 Propagation of quantization error in performing intra-prediction with deep learning

Raz Birman, Yoram Segal, Avishay David-Malka, Ofer Hadar, Ron Shmueli

Proceedings Volume 11137, Applications of Digital Image Processing XLII; 111370Z (2019) https://doi.org/10.1117/12.2530341
Event: SPIE Optical Engineering + Applications, 2019, San Diego, California, United States

Abstract

Standard video compression algorithms use multiple “Modes”, which are various linear combinations of pixels for prediction of their neighbors within image Macro-Blocks (MBs). In this research, we are using Deep Neural Networks (DNN) with supervised learning to predict block pixels. Using DNNs and employing intra-block pixel values’ calculations that penetrate into the block, we manage to obtain improved predictions that yield up to 200% reduction of residual block errors. However, using intra-block pixels for predictions brings upon interesting tradeoffs between prediction errors and quantization errors. We explore and explain these tradeoffs for two different DNN types. We further discovered that it is possible to achieve a larger dynamic range of quantization parameter (Qp) and thus reach lower bit-rates than standard modes, which already saturate at these Qp levels. We explore this phenomenon and explain its reasoning.

Conference Presentation

Citation Download Citation

Raz Birman, Yoram Segal, Avishay David-Malka, Ofer Hadar, and Ron Shmueli "Propagation of quantization error in performing intra-prediction with deep learning", Proc. SPIE 11137, Applications of Digital Image Processing XLII, 111370Z (6 September 2019); https://doi.org/10.1117/12.2530341

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available