English

6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference

Computer Vision and Pattern Recognition 2020-07-17 v2 Machine Learning Robotics Image and Video Processing

Abstract

We present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses. In highly ambiguous environments, which can easily arise due to symmetries and repetitive structures in the scene, computing one plausible solution (what most state-of-the-art methods currently regress) may not be sufficient. Instead we predict multiple camera pose hypotheses as well as the respective uncertainty for each prediction. Towards this aim, we use Bingham distributions, to model the orientation of the camera pose, and a multivariate Gaussian to model the position, with an end-to-end deep neural network. By incorporating a Winner-Takes-All training scheme, we finally obtain a mixture model that is well suited for explaining ambiguities in the scene, yet does not suffer from mode collapse, a common problem with mixture density networks. We introduce a new dataset specifically designed to foster camera localization research in ambiguous environments and exhaustively evaluate our method on synthetic as well as real data on both ambiguous scenes and on non-ambiguous benchmark datasets. We plan to release our code and dataset under \href\href{https://multimodal3dvision.github.io}{multimodal3dvision.github.io}.

Keywords

Cite

@article{arxiv.2004.04807,
  title  = {6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference},
  author = {Mai Bui and Tolga Birdal and Haowen Deng and Shadi Albarqouni and Leonidas Guibas and Slobodan Ilic and Nassir Navab},
  journal= {arXiv preprint arXiv:2004.04807},
  year   = {2020}
}

Comments

Accepted for publication at ECCV 2020. Project page under https://multimodal3dvision.github.io

R2 v1 2026-06-23T14:46:17.626Z