Unsupervised Depth Learning in Challenging Indoor Video: Weak Rectification to Rescue

    Bian Jia-Wang
    Bian Jia-Wang
    Zhan Huangying
    Zhan Huangying
    Wang Naiyan
    Wang Naiyan
    Cited by: 0|Bibtex|Views21|Links

    Abstract:

    Single-view depth estimation using CNNs trained from unlabelled videos has shown significant promise. However, the excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices, in which case the ego-motion is often degen...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments