S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction
This addresses the challenge of robust local feature extraction for computer vision tasks, especially under rotations, representing an incremental improvement over existing methods.
The paper tackled the problem of local feature extraction by introducing S-TREK, a method combining a translation and rotation equivariant keypoint detector with a lightweight descriptor, which outperformed state-of-the-art methods in benchmarks, particularly for in-plane rotations.
In this work we introduce S-TREK, a novel local feature extractor that combines a deep keypoint detector, which is both translation and rotation equivariant by design, with a lightweight deep descriptor extractor. We train the S-TREK keypoint detector within a framework inspired by reinforcement learning, where we leverage a sequential procedure to maximize a reward directly related to keypoint repeatability. Our descriptor network is trained following a "detect, then describe" approach, where the descriptor loss is evaluated only at those locations where keypoints have been selected by the already trained detector. Extensive experiments on multiple benchmarks confirm the effectiveness of our proposed method, with S-TREK often outperforming other state-of-the-art methods in terms of repeatability and quality of the recovered poses, especially when dealing with in-plane rotations.