Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation

Gil Avraham, Julian Straub, Tianwei Shen, Tsun-Yi Yang, Hugo Germain, Chris Sweeney, Vasileios Balntas, David Novotný, Daniel DeTone, Richard A. Newcombe

CVPRW 2022 pp. 5057-5066

doi:10.1109/CVPRW56347.2022.00554 /cvprw/2022/avraham2022cvprw-nerfels/

Abstract

This paper presents a framework that combines traditional keypoint-based camera pose optimization with an invertible neural rendering mechanism. Our proposed 3D scene representation, Nerfels, is locally dense yet globally sparse. As opposed to existing invertible neural rendering systems which overfit a model to the entire scene, we adopt a feature-driven approach for representing scene-agnostic, local 3D patches with renderable codes. By modelling a scene only where local features are detected, our framework effectively generalizes to unseen local regions in the scene via an optimizable code conditioning mechanism in the neural renderer, all while maintaining the low memory footprint of a sparse 3D map representation. Our model can be incorporated to existing state-of-the-art hand-crafted and learned local feature pose estimators, yielding improved performance when evaluating on ScanNet for wide camera baseline scenarios.

PDF CVPRW Semantic Scholar

Cite

Text

Avraham et al. "Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00554

Markdown

[Avraham et al. "Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/avraham2022cvprw-nerfels/) doi:10.1109/CVPRW56347.2022.00554

BibTeX

@inproceedings{avraham2022cvprw-nerfels,
  title     = {{Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation}},
  author    = {Avraham, Gil and Straub, Julian and Shen, Tianwei and Yang, Tsun-Yi and Germain, Hugo and Sweeney, Chris and Balntas, Vasileios and Novotný, David and DeTone, Daniel and Newcombe, Richard A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {5057-5066},
  doi       = {10.1109/CVPRW56347.2022.00554},
  url       = {https://mlanthology.org/cvprw/2022/avraham2022cvprw-nerfels/}
}