Extending Absolute Pose Regression to Multiple Scenes

Abstract

Direct pose regression using deep convolutional neural networks has become a highly active research area. However, even with significant improvements in performance in recent years, the best performance comes from training distinct, scene-specific networks. We propose a novel architecture, Multi-Scene PoseNet (MSPN), that allows for a single network to be used on an arbitrary number of scenes with only a small scene-specific component. Using our approach, we achieve competitive performance for two bench-mark 6DOF datasets, Microsoft 7Scenes and Cambridge Landmarks, while reducing the total number of network parameters significantly. Additionally, we demonstrate that our trained model serves as a better initialization for fine-tuning on new scenes compared to the standard ImageNet initialization, converging to lower error solutions within only a few epochs.

Cite

Text

Blanton et al. "Extending Absolute Pose Regression to Multiple Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00027

Markdown

[Blanton et al. "Extending Absolute Pose Regression to Multiple Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/blanton2020cvprw-extending/) doi:10.1109/CVPRW50498.2020.00027

BibTeX

@inproceedings{blanton2020cvprw-extending,
  title     = {{Extending Absolute Pose Regression to Multiple Scenes}},
  author    = {Blanton, Hunter and Greenwell, Connor and Workman, Scott and Jacobs, Nathan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {170-178},
  doi       = {10.1109/CVPRW50498.2020.00027},
  url       = {https://mlanthology.org/cvprw/2020/blanton2020cvprw-extending/}
}