Share Email Print

Proceedings Paper

AV1 In-loop super-resolution framework
Author(s): Urvang Joshi; Debargha Mukherjee; Yue Chen; Sarah Parker; Adrian Grange; Hui Su
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The AV1 codec added a new in-loop super-resolution mode that allows a frame to be encoded at a lower resolution, and then super-resolved normatively to the full resolution, before updating the reference buffers. While encoding at lower resolution and super-resolving to a higher resolution is not a new concept, this is the first time such a mode has been normatively incorporated in a standardized video codec. To this end, AV1 has not only added support for across-scale motion prediction to allow predicting a lower resolution version of a frame from higher resolution reference buffers, but also made various simplifications to the super-resolving process itself after reconstruction to make it both software and hardware-friendly in implementation. Specifically, the super-resolving process in AV1 comprises of normative linear upscaling, followed by a restoration operation to recover the high frequencies using another AV1 tool called loop-restoration that includes a Wiener or Self-guided filter selected in a block switchable manner. Further, in order to enable a cost-effective hardware solution with limited line-buffers, this mode only allows the upscaling/downscaling operation to be horizontal.

In this paper, we provide the details of the super-resolution mode in AV1 and some results showcasing the benefits of the same.

Paper Details

Date Published: 6 September 2019
PDF: 11 pages
Proc. SPIE 11137, Applications of Digital Image Processing XLII, 1113718 (6 September 2019); doi: 10.1117/12.2534538
Show Author Affiliations
Urvang Joshi, Google (United States)
Debargha Mukherjee, Google (United States)
Yue Chen, Google (United States)
Sarah Parker, Google (United States)
Adrian Grange, Google (United States)
Hui Su, Google (United States)

Published in SPIE Proceedings Vol. 11137:
Applications of Digital Image Processing XLII
Andrew G. Tescher; Touradj Ebrahimi, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?