Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion

Links: arxiv, video, bibtex

Abtract

Self-supervised learning has emerged as a powerful tool for depth and ego-motion estimation, leading to state-of-the-art results on benchmark datasets. However, one significant limitation shared by current methods is the assumption of a known parametric camera model – usually the standard pinhole geometry – leading to failure when applied to imaging systems that deviate significantly from this assumption (e.g., catadioptric cameras or underwater imaging). In this work, we show that self-supervision can be used to learn accurate depth and ego-motion estimation without prior knowledge of the camera model. Inspired by the geometric model of Grossberg and Nayar, we introduce Neural Ray Surfaces (NRS), convolutional networks that represent pixel-wise projection rays, approximating a wide range of cameras. NRS are fully differentiable and can be learned end-to-end from unlabeled raw videos. We demonstrate the use of NRS for self-supervised learning of visual odometry and depth estimation from raw videos obtained using a wide variety of camera systems, including pinhole, fisheye, and catadioptric.

Video

Bibtex

@inproceedings{vasiljevic2020neural,
    title={End-to-end Birds-eye-view Flow Estimation for Autonomous Driving},
    author={Igor Vasiljevic and Vitor Guizilini and Rares Ambrus and Sudeep Pillai
        and Wolfram Burgard and Greg Shakhnarovich and Adrien Gaidon},
    booktitle={3DV},
    year={2020},
}