2023 · 14 citations · 30 references
ComputingComputer ScienceComputer VisionFeature EngineeringRobot VisionDeep LearningFeature DescriptionObject RecognitionPose EstimationRepresentation LearningRotation RepresentationsInvariant Feature DescriptorsKeypoint DescriptorsKeypoint DetectionKeypoint LocalizationLocal Feature DescriptorsLocal Feature DetectionRotations
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.
30
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Object recognition from local scale-invariant features
David Lowe · 1999 · 16.2K citations
Advances in neural information processing systems 7
Computers & Mathematics with Applications · 1996 · 14.4K citations
A Combined Corner and Edge Detector
Chris Harris, Matthew J. Stephens · 1988 · 12.5K citations
ORB: An efficient alternative to SIFT or SURF
Ethan Rublee, Vincent Rabaud, Kurt Konolige et al. · 2011 · 10.4K citations