CVPR 2020 Workshop: VisLocOdomMap

Extending Absolute Pose Regression to Multiple Scenes

Hunter Blanton, Connor Greenwell, Scott Workman, Nathan Jacobs

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 benchmark 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.

Document Preview

Paper thumbnails

Project Details

Supplementary content

Oral Presentation

Citation

BibTeX entry

@inproceedings{blanton2020extending,
  author={Hunter Blanton and Connor Greenwell and Scott Workman and Nathan Jacobs},
  title={{Extending Absolute Pose Regression to Multiple Scenes}},
  booktitle={{CVPR Workshop: Long-Term Visual Localization, Visual Odometry and Geometric and Learning-based SLAM}},
  year={2020}
}