HARA: A Hierarchical Approach for Robust Rotation Averaging
This addresses robust rotation estimation in computer vision, which is incremental but with strong specific gains.
The paper tackles the problem of robust multiple rotation averaging by proposing HARA, a hierarchical approach that builds a spanning tree based on triplet support to reduce outlier inclusion. The method achieves state-of-the-art results on synthetic and real datasets.
We propose a novel hierarchical approach for multiple rotation averaging, dubbed HARA. Our method incrementally initializes the rotation graph based on a hierarchy of triplet support. The key idea is to build a spanning tree by prioritizing the edges with many strong triplet supports and gradually adding those with weaker and fewer supports. This reduces the risk of adding outliers in the spanning tree. As a result, we obtain a robust initial solution that enables us to filter outliers prior to nonlinear optimization. With minimal modification, our approach can also integrate the knowledge of the number of valid 2D-2D correspondences. We perform extensive evaluations on both synthetic and real datasets, demonstrating state-of-the-art results.