Robust Two-View Geometry Estimation with Implicit Differentiation
This work addresses the problem of robust geometry estimation for computer vision applications, offering a novel integration of components but is incremental in its approach.
The authors tackled robust two-view geometry estimation by introducing a differentiable robust loss function fitting and an implicit layer for fundamental matrix estimation, which improved numerical stability and integrated feature extraction, matching, and geometry estimation into an end-to-end trainable pipeline. Their method outperformed classic and learning-based state-of-the-art approaches by a large margin in camera pose estimation tasks across outdoor and indoor datasets.
We present a novel two-view geometry estimation framework which is based on a differentiable robust loss function fitting. We propose to treat the robust fundamental matrix estimation as an implicit layer, which allows us to avoid backpropagation through time and significantly improves the numerical stability. To take full advantage of the information from the feature matching stage we incorporate learnable weights that depend on the matching confidences. In this way our solution brings together feature extraction, matching and two-view geometry estimation in a unified end-to-end trainable pipeline. We evaluate our approach on the camera pose estimation task in both outdoor and indoor scenarios. The experiments on several datasets show that the proposed method outperforms both classic and learning-based state-of-the-art methods by a large margin. The project webpage is available at: https://github.com/VladPyatov/ihls