于源,贾克斌.基于 T-CNN 的 3D-HEVC 深度图帧内快速编码算法[J].高技术通讯(中文),2023,33(10):1068~1076 |
基于 T-CNN 的 3D-HEVC 深度图帧内快速编码算法 |
Fast intra coding algorithm for 3D-HEVC depth map based on T-CNN |
|
DOI:3772/ j. issn. 1002-0470. 2023. 10. 007 |
中文关键词: 3D-HEVC;深度图;帧内编码;卷积神经网络 |
英文关键词: 3D-HEVC, depth map, intra-frame coding, convolutional neural network |
基金项目: |
作者 | 单位 | 于源 | (北京工业大学信息学部北京 100124)
(北京工业大学计算智能与智能系统北京市重点实验室北京 100124)
(先进信息网络北京实验室北京 100124) | 贾克斌 | |
|
摘要点击次数: 930 |
全文下载次数: 709 |
中文摘要: |
3D-HEVC标准中引入了具有大面积平坦区域、陡峭边缘和低纹理复杂度特性的深度图。针对深度图编码过程中编码单元(CU)率失真优化导致编码复杂度过高这一问题,本文在分析深度图编码所具有的特点的基础上,构建了深度图划分深度数据集,并提出了一种基于两通道特征传递卷积神经网络(T-CNN)的划分深度预测算法。使用本文提出的算法替换原始编码器中各视点下深度图CU划分模块,可以在一定的率失真性能损失下,将原始HTM-16.0编码器编码时间平均减少76%左右,编码效率得到了显著提升。 |
英文摘要: |
Depth maps with large flat areas, steep edges, and low texture complexity have been introduced into the 3D-HEVC standard. To solve the problem of high encoding complexity caused by coding unit (CU) rate-distortion optimization of the depth map, a depth map partition dataset is constructed by analyzing the characteristics of the coding process of depth map. And a partition depth prediction algorithm is proposed based on the two-channel feature transfer convolutional neural network (T-CNN). The CU division process of the depth map is replaced by the proposed algorithm under each viewpoint in the original encoder, and the encoding time of the original HTM-16.0 encoder is reduced by about 76% on average with certain loss of rate-distortion performance. It shows that the proposed algorithm significantly improves the coding efficiency. |
查看全文
查看/发表评论 下载PDF阅读器 |
关闭 |