Self-Supervised Learning of Depth and Camera Motion from 360 Videos

Self-Supervised Learning of Depth and Camera
Motion from 360 Videos

Fu-En Wang*, Hou-Ning Hu*, Hsien-Tzu Cheng*, Juan-Ting Lin,
Shang-Ta Yang, Meng-Li Shih, Hung-Kuo Chu, Min Sun, (*indicate equal contribution)

Dept. of Electrical Engineering, National Tsing Hua University, Taiwan
Dept. of Computer Science, National Tsing Hua University, Taiwan

Abstract

As 360 cameras become prevalent in many autonomous systems (e.g., self-driving cars and drones), efficient 360 perception becomes more and more important. We propose a novel self-supervised learning approach for predicting the omnidirectional depth and camera motion from a 360 video. In particular, starting from the SfMLearner, which is designed for cameras with normal field-of-view, we introduce three key features to process 360 images efficiently. Firstly, we convert each image from equirectangular projection to cubic projection in order to avoid image distortion. In each network layer, we use Cube Padding (CP), which pads intermediate features from adjacent faces, to avoid image boundaries. Secondly, we propose a novel ``spherical" photometric consistency constraint on the whole viewing sphere. In this way, no pixel will be projected outside the image boundary which typically happens in images with normal field-of-view. Finally, rather than naively estimating six independent camera motions (i.e., naively applying SfM-Learner to each face on a cube), we propose a novel camera pose consistency loss to ensure the estimated camera motions reaching consensus. To train and evaluate our approach, we collect a new PanoSUNCG dataset containing a large amount of 360 videos with groundtruth depth and camera motion. Our approach achieves state-of-the-art depth prediction and camera motion estimation on PanoSUNCG with faster inference speed comparing to equirectangular. In real-world indoor videos, our approach can also achieve qualitatively reasonable depth prediction by acquiring model pre-trained on PanoSUNCG.

ACCV 2018 Oral

Self-Supervised Learning of Depth and Camera Motion from 360 Videos

Fu-En Wang*

Hou-Ning Hu*

Hsien-Tzu Cheng*

Juan-Ting Lin

Shang-Ta Yang

Meng-Li Shih

Hung-Kuo Chu

Min Sun

Paper (arXiv)

Poster

@inproceedings{wang2019self,
  title={Self-supervised learning of depth and camera motion from 360 videos},
  author={Wang, Fu-En and Hu, Hou-Ning and Cheng, Hsien-Tzu and Lin, Juan-Ting and Yang, Shang-Ta and Shih, Meng-Li and Chu, Hung-Kuo and Sun, Min},
  booktitle={Computer Vision--ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2--6, 2018, Revised Selected Papers, Part V},
  pages={53--68},
  year={2019},
  organization={Springer}
}