Corpus ID: 211010487

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

@article{Yin2020DiverseDepthAD,
  title={DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data},
  author={Wei Yin and Xinlong Wang and Chunhua Shen and Yifan Liu and Zeyong Tian and Songcen Xu and Changming Sun and Dou Renyin},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.00569}
}

Wei Yin, Xinlong Wang, +5 authors Dou Renyin

Published 2020

Computer Science

ArXiv

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or further) can enjoy better generalization, with the price of failing to recover the accurate geometric shape of the scene. In this work, we propose a… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed