A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution
The joint video exploration team (JVET) proposed versatile video coding (VVC) as a new video coding standard, and its quadtree plus multi-type tree (QTMTT) partition structure brings effective coding performance improvements.However, it brings about a sharp increase in encoding complexity, which gre...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2023-07-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023132/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530854479757312 |
|---|---|
| author | Zhen YE Guoxiang WANG Junfeng SONG Haokun LIU Tiansong LI |
| author_facet | Zhen YE Guoxiang WANG Junfeng SONG Haokun LIU Tiansong LI |
| author_sort | Zhen YE |
| collection | DOAJ |
| description | The joint video exploration team (JVET) proposed versatile video coding (VVC) as a new video coding standard, and its quadtree plus multi-type tree (QTMTT) partition structure brings effective coding performance improvements.However, it brings about a sharp increase in encoding complexity, which greatly increases the encoding time.In order to solve the above problems, a fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution was proposed.The pixel of coding unit (CU) was used as input, and the texture information feature of CU was extracted through depth-separable convolution.Therefore, accurate partition mode prediction was realized in the QTMT structure in VVC, and the complexity of the encoder was reduced by skipping low-probability partition modes.Experimental results show that the proposed algorithm saves 18% to 48% of encoding time on the VTM 15.2, and only brings an average performance loss of 0.15%.And the additional complexity brought by the lightweight depthwise separable convolution calculation is also negligible. |
| format | Article |
| id | doaj-art-b5cfba351d2946f4afca9a2d4fa428ff |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2023-07-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-b5cfba351d2946f4afca9a2d4fa428ff2025-01-15T02:58:26ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-07-01399910859563785A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolutionZhen YEGuoxiang WANGJunfeng SONGHaokun LIUTiansong LIThe joint video exploration team (JVET) proposed versatile video coding (VVC) as a new video coding standard, and its quadtree plus multi-type tree (QTMTT) partition structure brings effective coding performance improvements.However, it brings about a sharp increase in encoding complexity, which greatly increases the encoding time.In order to solve the above problems, a fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution was proposed.The pixel of coding unit (CU) was used as input, and the texture information feature of CU was extracted through depth-separable convolution.Therefore, accurate partition mode prediction was realized in the QTMT structure in VVC, and the complexity of the encoder was reduced by skipping low-probability partition modes.Experimental results show that the proposed algorithm saves 18% to 48% of encoding time on the VTM 15.2, and only brings an average performance loss of 0.15%.And the additional complexity brought by the lightweight depthwise separable convolution calculation is also negligible.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023132/video codingdeep learningintra codingcoding unit division |
| spellingShingle | Zhen YE Guoxiang WANG Junfeng SONG Haokun LIU Tiansong LI A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution Dianxin kexue video coding deep learning intra coding coding unit division |
| title | A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution |
| title_full | A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution |
| title_fullStr | A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution |
| title_full_unstemmed | A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution |
| title_short | A fast block partitioning algorithm for VVC intra coding based on depthwise separable convolution |
| title_sort | fast block partitioning algorithm for vvc intra coding based on depthwise separable convolution |
| topic | video coding deep learning intra coding coding unit division |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023132/ |
| work_keys_str_mv | AT zhenye afastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT guoxiangwang afastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT junfengsong afastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT haokunliu afastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT tiansongli afastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT zhenye fastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT guoxiangwang fastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT junfengsong fastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT haokunliu fastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution AT tiansongli fastblockpartitioningalgorithmforvvcintracodingbasedondepthwiseseparableconvolution |