文献类型：期刊文献

英文题名：Attention-based context aggregation network for monocular depth estimation

作者：Chen, Yuru[1];Zhao, Haitao[1];Hu, Zhengwei[1];Peng, Jingchao[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China

年份：2021

卷号：12

期号：6

起止页码：1583

外文期刊名：INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS

收录：;EI(收录号：20210109720439);WOS:【SCI-EXPANDED(收录号:WOS:000604481400006)】；

语种：英文

外文关键词：Depth estimation; Attention model; Context aggregation; Convolutional neural networks; Deep learning

摘要：Depth estimation is a traditional computer vision task, which plays a crucial role in understanding 3D scene geometry. Recently, algorithms that combine the multi-scale features extracted by the dilated convolution based block (atrous spatial pyramid pooling, ASPP) have gained significant improvements in depth estimation. However, the discretized and predefined dilation kernels cannot capture the continuous context information that differs in diverse scenes and easily introduce the grid artifacts. This paper proposes a novel algorithm, called attention-based context aggregation network (ACAN) for depth estimation. A supervised self-attention model is designed and utilized to adaptively learn the task-specific similarities between different pixels to model the continuous context information. Moreover, a soft ordinal inference is proposed to transform the predicted probabilities to continuous depth values which reduce the discretization error (about 1% decrease in RMSE). ACAN achieves state-of-the-art performance on public monocular depth-estimation benchmark datasets. The source code of ACAN can be found in .