paper-with-me

홈 › Papers

Self-Supervised Learning of Image Scale and Orientation

2022-06-15 · Jongmin Lee, Yoonwoo Jeong, Minsu Cho

We study the problem of learning to assign a characteristic pose, i.e., scale and orientation, for an image region of interest. Despite its apparent simplicity, the problem is non-trivial; it is hard to obtain a large-scale set of image regions with explicit pose annotations that a model directly learns from. To tackle the issue, we propose a self-supervised learning framework with a histogram alignment technique. It generates pairs of image patches by random rescaling/rotating and then train an estimator to predict their scale/orientation values so that their relative difference is consistent with the rescaling/rotating used. The estimator learns to predict a non-parametric histogram distribution of scale/orientation without any supervision. Experiments show that it significantly outperforms previous methods in scale/orientation estimation and also improves image matching and 6 DoF camera pose estimation by incorporating our patch poses into a matching process.

📄 PDF Abstract BibTeX arXiv:2206.07259

Code (1)

bluedream1121/self-sca-ori 공식 구현 pytorch

Tasks

Camera Pose EstimationPose EstimationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Learning Soft Estimator of Keypoint Scale and Orientation With Probabilistic Covariant Loss

2022-01-01 · CVPR 2022 1 · Pei Yan, Yihua Tan, Shengzhou Xiong, Yuan Tai 외

Estimating keypoint scale and orientation is crucial to extracting invariant features under significant geometric changes. Recently, the estimators based on self-supervised learning have been designed to adapt to com…

3D ReconstructionSelf-Supervised Learning

Self-Supervised Equivariant Learning for Oriented Keypoint Detection

2022-04-19 · CVPR 2022 1 · Jongmin Lee, Byungjin Kim, Minsu Cho

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. Exist…

Camera Pose EstimationKeypoint DetectionPose EstimationSelf-Supervised Learning+1

Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms

2021-05-29 · Shivin Devgon, Jeffrey Ichnowski, Ashwin Balakrishna, Harry Zhang 외

Orienting objects is a critical component in the automation of many packing and assembly tasks. We present an algorithm to orient novel objects given a depth image of the object in its current and desired orientation. We…

Self-Supervised Learning

Deep Projective Rotation Estimation through Relative Supervision

2022-11-21 · Brian Okorn, Chuer Pan, Martial Hebert, David Held

Orientation estimation is the core to a variety of vision and robotics tasks such as camera and object pose estimation. Deep learning has offered a way to develop image-based orientation estimators; however, such estimat…

Pose EstimationSelf-Supervised Learning

ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects

2025-12-10 · Woojin Lee, Hyugjae Chang, Jaeho Moon, Jaehyup Lee 외 arxiv

Weakly supervised oriented object detection (WS-OOD) has gained attention as a cost-effective alternative to fully supervised methods, providing both efficiency and high accuracy. Among weakly supervised approaches, hori…

Self-Supervised LearningObject Detection