Direct-PoseNet

Absolute Pose Regression with Photometric Consistency

arXiv 2021


Active Vision Lab, University of Oxford

Active Vision Lab, University of Oxford

Active Vision Lab, University of Oxford


Paper


Abstract

We present a relocalization pipeline, which combines an absolute pose regression (APR) network with a novel view synthesis based direct matching module, offering superior accuracy while maintaining low inference time. Our contribution is twofold: i) we design a direct matching module that supplies a photometric supervision signal to refine the pose regression network via differentiable rendering; ii) we modify the rotation representation from the classical quaternion to SO(3) in pose regression, removing the need for balancing rotation and translation loss terms. As a result, our network Direct-PoseNet achieves state-of-the-art performance among all other single-image APR methods on the 7-Scenes benchmark and the LLFF dataset.

Architecture

Direct-PoseNet

Results


Citation

      @article{chen21directPN,
        title={Direct-{P}ose{N}et: Absolute Pose Regression with Photometric Consistency},
        author={Chen, Shuai and Wang, Zirui and Prisacariu, Victor Adrian},
        journal={arxiv arXiv:2104.04073},
        year={2021},
      }