RoMa: Robust Dense Feature Matching

Johan Edstedt1, Qiyu Sun2, Georg Bökman3, Mårten Wadenbäck1, Michael Felsberg1
1Linköping University    2East China University of Science and Technology    3Chalmers University of Technology   
Paper Code
Visualization of RoMa estimated warps between large-baseline image pairs.
The animation is done by by parameterizing \(W(t) = (1-t) x^{\mathcal{A}} + t \hat{x}^{\mathcal{B}}\) .

Summary

We propose a significantly more robust dense feature matcher than previous approaches.

Method

Our approach consists of four main contributions (see figure above):

  1. We use a foundation model (DINOv2) instead of training from scratch, leading to more robust matches.
  2. We use a specialized ConvNet for fine features.
  3. We propose a Transformer match decoder that predicts anchor probabilities instead of coordinate regression.
  4. We use better losses.

BibTeX


      @article{edstedt2023roma,
        title={{RoMa: Robust Dense Feature Matching}},
        author={Edstedt, Johan and Sun, Qiyu and Bökman, Georg and Wadenbäck, Mårten and Felsberg, Michael},
        journal={arXiv preprint arXiv:2305.15404},
        year={2023}
        }