.png){kind=icon}
返回
Unsupervised Scale-Consistent Depth Learning from Video
.png){kind=icon}
OA
AI
DOI：10.1007/s11263-021-01484-6.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose a monocular depth estimation method SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions include: (i) we propose a geometry consistency loss, which penalizes the inconsistency of predicted depths between adjacent views; (ii) we propose a self-discovered mask to automatically localize moving objects that violate the underlying static scene assumption and cause noisy signals during training; (iii) we demonstrate the efficacy of each component with a detailed ablation study and show high-quality depth estimation results in both KITTI and NYUv2 datasets. Moreover, thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into ORB-SLAM2 system for more robust and accurate tracking. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training. Finally, we provide several demos for qualitative evaluation. The source code is released on GitHub.
Keyword:
Unsupervised depth estimation
Scale consistency
Visual SLAM
Pseudo-RGBD SLAM
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
分享收藏Different Forms of Vigilance in Response to the Presence of Predators and Conspecifics in a Group‐Living Mammal, the European Rabbit.png)
Ethology
EthologyIF0
PREAI
分享收藏Carboxylated pillar[n]arene (n= 5–7) host molecules: high affinity and selective binding in water
PREAI
分享收藏Perovskite solid electrolytes: Structure, transport properties and fuel cell applications钙钛矿固体电解质: 结构、输运性质和燃料电池应用
PREAI
分享收藏分享收藏
查看更多内容