.png){kind=icon}
返回
AGNet: Attention Guided Sparse Depth Completion Using Convolutional Neural Networks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3144596.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Sparse depth completion generates a dense depth image from its sparse measurement with the guidance of RGB image. In this paper, we propose attention guided sparse depth completion using convolutional neural networks, called AGNet. We adopt attention learning to get geometric cues for depth regression from RGB image and capture multi-scale depth structures. First, we use RGB image and valid binary mask from the input sparse depth image as input to generate an initial coarse depth image and its confidence map. Then, we generate attention map for depth refinement using a cross spatial attention module (CSAM). CSAM separately takes the RGB image with valid mask and invalid mask as input to make full use of color information in attention map. Next, we build a multi-scale learning network to encode the sparse depth image with different scales, thus leading to accurate depth completion. AGNet takes advantage of the input sparse depth image for encoding coarse features with a moderate model size. Experimental results show that AGNet achieves comparable performance with state-of-the-art methods for depth completion in NYU v2 dataset.
Keyword:
Feature extraction
Convolutional neural networks
Convolution
Spatial resolution
Image color analysis
Color
Task analysis
Depth completion
attention learning
convolutional neural networks
depth prediction
multi-scale learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
分享收藏Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression properties.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏
查看更多内容