.png){kind=icon}
返回
Unsupervised Monocular Depth Estimation Using Attention and Multi-Warp Reconstruction
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2021.3091308.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Monocular depth estimation has become one of the most studied topics in computer vision. Most approaches treat depth prediction as a fully supervised regression problem requiring vast amounts of corresponding ground-truth depth and image pairs for training. Unsupervised monocular depth estimation has emerged as a promising alternative that eliminates dataset limitations. This paper proposes an end-to-end unsupervised deep learning framework integrating attention blocks and multi-warp loss for monocular depth estimation. In this framework, to explore more general contextual information among the feature volumes, an attention block that sequentially refines the feature maps along the channel and spatial dimensions is inserted after the first and last stages of the network encoder. Additionally, to further utilize the errors in the original disparity estimation from the network, a novel multi-warp reconstruction strategy is designed for the loss function. The experimental results evaluated on the KITTI, CityScapes and Make3D datasets demonstrate the state-of-the-art performance and satisfactory generalization ability of our proposed method.
Keyword:
Estimation
Image reconstruction
Convolution
Task analysis
Training
Videos
Unsupervised learning
Monocular depth estimation
unsupervised
attention
multi-Warp reconstruction
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
Carboxylated pillar[n]arene (n= 5–7) host molecules: high affinity and selective binding in water
PREAI
分享收藏Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm基于不确定性分析和Retinex算法的无监督单目深度估计方法.png)
SENSORS
OAAI
SENSORSIF3.5
OAAI分享收藏
查看更多内容