Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints

2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)(2021)

引用 6|浏览9
暂无评分
摘要
Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still plague these systems. To this end, this work presents an unsupervised learning framework that is able to predict at-scale depth maps and egomotion, in addition to camera intrinsics, from a sequence of monocular images via a single network. Our method incorporates both spatial and temporal geometric constraints to resolve depth and pose scale factors, which are enforced within the supervisory reconstruction loss functions at training time. Only unlabeled stereo sequences are required for training the weights of our single-network architecture, which reduces overall implementation overhead as compared to previous methods. Our results demonstrate strong performance when compared to the current state-of-the-art on multiple sequences of the KITTI driving dataset and can provide faster training times with its reduced network complexity.
更多
查看译文
关键词
spatio-temporal constraints,monocular depth inference,time-of-flight sensors,scale acquisition,at-scale depth maps,egomotion,camera intrinsics,monocular images,spatial constraints,temporal geometric constraints,scale factors,supervisory reconstruction loss functions,training time,unlabeled stereo sequences,single-network architecture,implementation overhead,multiple sequences,training times,reduced network complexity,unsupervised monocular depth learning,integrated intrinsics,KITTI driving dataset
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要