海军航空大学学报2024，Vol.39Issue(2)：241-248,8.DOI:10.7682/j.issn.2097-1427.2024.02.007
自适应融合RGB图像特征的稀疏深度修复
Adaptive Fusion of RGB Image Features for Sparse Depth Completion
周恒 1李滔 1孙明明 1武丹丹1
作者信息
- 1. 西华大学电气与电子信息学院,四川 成都 610039
- 折叠
摘要
Abstract
The purpose of depth completion is to restore dense depth images from sparse depth images.Existing methods usually take sparse depth images and their corresponding RGB images as input and restore dense depth images through a convolutional neural network.However,ordinary convolutional layers have large limitations in dealing with sparse and ir-regular depth information,while RGB image features and depth image features belong to different modalities.To address these problems,an adaptive sparse invariant module to handle sparse depths according to the validity of the input pixels is proposed.The multi-scale features fusion incorporating attention mechanism is also proposed to further improve the depth completion performance by suppressing unnecessary features while focusing on effective features.A series of experiments are conducted on the NYUv2 dataset,and the experimental results demonstrate the effectiveness of the proposed algo-rithm and module.关键词
深度图像修复/特征融合/室内场景/注意力机制Key words
depth completion/feature fusion/indoor scenes/attention mechanism分类
信息技术与安全科学引用本文复制引用
周恒,李滔,孙明明,武丹丹..自适应融合RGB图像特征的稀疏深度修复[J].海军航空大学学报,2024,39(2):241-248,8.
