Self-Supervised Equivariant Learning for Oriented Keypoint Detection
This addresses the issue of unreliable keypoint detection against geometric variations for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting robust oriented keypoints in images, which is crucial for tasks like image matching and camera pose estimation, by introducing a self-supervised learning framework using rotation-equivariant CNNs and a dense orientation alignment loss, resulting in outperformance on benchmarks.
Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synthetic transformations for training a histogram-based orientation map. Our method outperforms the previous methods on an image matching benchmark and a camera pose estimation benchmark.