Sorry, you need to enable JavaScript to visit this website.

Intra Block Partition Structure Prediction via Convolutional Neural Network

Primary tabs

Citation Author(s):
Xu Han, Shanshe Wang, Yong Chen, Siwei Ma, Wen Gao
Submitted by:
Xu Han
Last updated:
1 March 2021 - 10:02am
Document Type:
Presentation Slides
Document Year:
Presenters Name:
Xu Han



In video coding, block partition segments image into non-overlap blocks for individual coding, the structure of which is becoming more and more flexible along with the development of video coding standards. Multiple types of tree structures have been proposed recently, which extensively improved the complexity of the encoding process due to recursive rate-distortion search for the optimal partition. In this paper, a two-stage Convolutional Neural Network (CNN) based partition structure prediction method is proposed to bypass the decision process of the block size in intra frame coding. Specifically, the Coding Unit (CU) partition is first represented in 4x4 sub-block granularity and predicted by the end-to-end trained CNNs. Then, the final partition structure compatible with the coding standard is derived from the prediction results directly. Experimental results show that the proposed CNN based partition method achieves about 56 times speedup (97% time-saving) with 9% BD-rate degradation against the reference software of the latest AVS3 coding standard (IEEE Standard 1857.10).

0 users have voted:

Dataset Files

Presentation slides