English

Self-Supervised Camera Self-Calibration from Video

Computer Vision and Pattern Recognition 2022-03-03 v2 Robotics

Abstract

Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams. In practice, calibration is a laborious procedure requiring specialized data collection and careful tuning. This process must be repeated whenever the parameters of the camera change, which can be a frequent occurrence for mobile robots and autonomous vehicles. In contrast, self-supervised depth and ego-motion estimation approaches can bypass explicit calibration by inferring per-frame projection models that optimize a view synthesis objective. In this paper, we extend this approach to explicitly calibrate a wide range of cameras from raw videos in the wild. We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods. We validate our approach on a wide variety of camera geometries, including perspective, fisheye, and catadioptric. Finally, we show that our approach leads to improvements in the downstream task of depth estimation, achieving state-of-the-art results on the EuRoC dataset with greater computational efficiency than contemporary methods.

Keywords

Cite

@article{arxiv.2112.03325,
  title  = {Self-Supervised Camera Self-Calibration from Video},
  author = {Jiading Fang and Igor Vasiljevic and Vitor Guizilini and Rares Ambrus and Greg Shakhnarovich and Adrien Gaidon and Matthew R. Walter},
  journal= {arXiv preprint arXiv:2112.03325},
  year   = {2022}
}

Comments

The project page: https://sites.google.com/ttic.edu/self-sup-self-calib

R2 v1 2026-06-24T08:06:38.631Z