A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet

As an extension of HEVC, 3D-HEVC retains the quadtree structure inherent to HEVC and is currently recognized as the most widely adopted international standard for stereoscopic video coding. In intra coding, quadtree partitioning is determined recursively through rate-distortion cost calculations. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Erlin Tian, Jiabao Zhang, Qiuwen Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11045913/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426106649673728
author Erlin Tian
Jiabao Zhang
Qiuwen Zhang
author_facet Erlin Tian
Jiabao Zhang
Qiuwen Zhang
author_sort Erlin Tian
collection DOAJ
description As an extension of HEVC, 3D-HEVC retains the quadtree structure inherent to HEVC and is currently recognized as the most widely adopted international standard for stereoscopic video coding. In intra coding, quadtree partitioning is determined recursively through rate-distortion cost calculations. This process demands extensive computational resources and results in high encoding complexity. To mitigate this challenge, the present paper proposes a deep learning-based encoding algorithm designed to replace the intricate coding unit (CU) partitioning process utilized in HTM. First, we introduce the Mean Absolute Difference (MAD), which quantifies the dispersion of pixel values around the mean within a given region. By calculating the ratio of a coding unit&#x2019;s MAD to its pixel mean, we categorize <inline-formula> <tex-math notation="LaTeX">$64\times 64$ </tex-math></inline-formula> CUs into smooth and complex CUs. For smooth CUs, partitioning is terminated prematurely to minimize redundant rate-distortion optimization (RDO) computations. In contrast, for complex CUs, we propose a lightweight ResNet (Residual Neural Network) model that substitutes standard convolutions with depthwise separable convolutions (DSC) in order to decrease the number of parameters. This model effectively integrates both local and global features to generate partitioning predictions at various depths, while incorporating the quantization parameter (QP) into the input to enhance prediction accuracy. Experimental results indicate that, in comparison to the original HTM-16.2 method, the proposed approach achieves a reduction in encoding time of 48.16%, while only resulting in an increase of 0.28% in BDBR.
format Article
id doaj-art-2156cde1f6a84b58a3d54f1e0086b876
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2156cde1f6a84b58a3d54f1e0086b8762025-08-20T03:29:34ZengIEEEIEEE Access2169-35362025-01-011311172211173210.1109/ACCESS.2025.358193011045913A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNetErlin Tian0Jiabao Zhang1https://orcid.org/0009-0009-1488-6897Qiuwen Zhang2https://orcid.org/0000-0002-8533-7088School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, ChinaAs an extension of HEVC, 3D-HEVC retains the quadtree structure inherent to HEVC and is currently recognized as the most widely adopted international standard for stereoscopic video coding. In intra coding, quadtree partitioning is determined recursively through rate-distortion cost calculations. This process demands extensive computational resources and results in high encoding complexity. To mitigate this challenge, the present paper proposes a deep learning-based encoding algorithm designed to replace the intricate coding unit (CU) partitioning process utilized in HTM. First, we introduce the Mean Absolute Difference (MAD), which quantifies the dispersion of pixel values around the mean within a given region. By calculating the ratio of a coding unit&#x2019;s MAD to its pixel mean, we categorize <inline-formula> <tex-math notation="LaTeX">$64\times 64$ </tex-math></inline-formula> CUs into smooth and complex CUs. For smooth CUs, partitioning is terminated prematurely to minimize redundant rate-distortion optimization (RDO) computations. In contrast, for complex CUs, we propose a lightweight ResNet (Residual Neural Network) model that substitutes standard convolutions with depthwise separable convolutions (DSC) in order to decrease the number of parameters. This model effectively integrates both local and global features to generate partitioning predictions at various depths, while incorporating the quantization parameter (QP) into the input to enhance prediction accuracy. Experimental results indicate that, in comparison to the original HTM-16.2 method, the proposed approach achieves a reduction in encoding time of 48.16%, while only resulting in an increase of 0.28% in BDBR.https://ieeexplore.ieee.org/document/11045913/3D-HEVCdepth mapintra codingResNet
spellingShingle Erlin Tian
Jiabao Zhang
Qiuwen Zhang
A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet
IEEE Access
3D-HEVC
depth map
intra coding
ResNet
title A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet
title_full A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet
title_fullStr A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet
title_full_unstemmed A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet
title_short A Low Complexity Algorithm for 3D-HEVC Depth Map Intra Coding Based on MAD and ResNet
title_sort low complexity algorithm for 3d hevc depth map intra coding based on mad and resnet
topic 3D-HEVC
depth map
intra coding
ResNet
url https://ieeexplore.ieee.org/document/11045913/
work_keys_str_mv AT erlintian alowcomplexityalgorithmfor3dhevcdepthmapintracodingbasedonmadandresnet
AT jiabaozhang alowcomplexityalgorithmfor3dhevcdepthmapintracodingbasedonmadandresnet
AT qiuwenzhang alowcomplexityalgorithmfor3dhevcdepthmapintracodingbasedonmadandresnet
AT erlintian lowcomplexityalgorithmfor3dhevcdepthmapintracodingbasedonmadandresnet
AT jiabaozhang lowcomplexityalgorithmfor3dhevcdepthmapintracodingbasedonmadandresnet
AT qiuwenzhang lowcomplexityalgorithmfor3dhevcdepthmapintracodingbasedonmadandresnet