Improving Image-Based Localization with Deep Learning: The Impact of the Loss Function

@article{Ward2019ImprovingIL,
  title={Improving Image-Based Localization with Deep Learning: The Impact of the Loss Function},
  author={Isaac Ronald Ward and M. A. Asim K. Jalwana and Mohammed Bennamoun},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.03692}
}
  • Isaac Ronald Ward, M. A. Asim K. Jalwana, Mohammed Bennamoun
  • Published 2019
  • Computer Science
  • ArXiv
  • This work investigates the impact of the loss function on the performance of Neural Networks, in the context of a monocular, RGB-only, image localization task. A common technique used when regressing a camera's pose from an image is to formulate the loss as a linear combination of positional and rotational mean squared error (using tuned hyperparameters as coefficients). In this work we observe that changes to rotation and position mutually affect the captured image, and in order to improve… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES

    Geometric Loss Functions for Camera Pose Regression with Deep Learning

    VIEW 3 EXCERPTS

    Modelling uncertainty in deep learning for camera relocalization

    VIEW 2 EXCERPTS

    Learning Less is More - 6D Camera Localization via 3D Surface Regression

    VIEW 2 EXCERPTS

    PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Random forests versus Neural Networks — What's best for camera localization?

    VIEW 1 EXCERPT

    Deep Auxiliary Learning for Visual Localization and Odometry

    VIEW 1 EXCERPT

    Image-Based Localization Using LSTMs for Structured Feature Correlation

    VIEW 3 EXCERPTS