Self-Supervised Equivariant Learning for Oriented Keypoint Detection
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.
Code (1)
Tasks
Camera Pose EstimationKeypoint DetectionPose EstimationSelf-Supervised LearningTranslationSimilar Papers 제목 키워드 기반
RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy
Unlike in natural images, in endoscopy there is no clear notion of an up-right camera orientation. Endoscopic videos therefore often contain large rotational motions, which require keypoint detection and description algo…
Keypoint DetectionPose EstimationSelf-Supervised LearningRotation-Equivariant Keypoint Detection
We show how to train a rotation-equivariant representation to extract local keypoints for image matching. Existing learning-based methods focused on extracting translation-equivariant keypoints using conventional convolu…
Keypoint DetectionTranslationUSEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation
Can a robot manipulate intra-category unseen objects in arbitrary poses with the help of a mere demonstration of grasping pose on a single object instance? In this paper, we try to address this intriguing challenge by us…
Keypoint DetectionObjectLearning Rotation-Equivariant Features for Visual Correspondence
Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to ext…
Camera Pose EstimationPose EstimationSelf-Supervised LearningSD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras
Event cameras offer many advantages over traditional frame-based cameras such as high dynamic range and low latency. Therefore event cameras are widely applied in diverse computer vision applications where event-base…
Keypoint Detection