Good Keypoints for the Two-View Geometry Estimation Problem
Local features are essential to many modern downstream applications. Therefore, it is of interest to determine the properties of local features that contribute to the downstream performance for a better design of feature detectors and descriptors. In our work, we propose a new theoretical model for scoring feature points (keypoints) in the context of the two-view geometry estimation problem. The model determines two properties that a good keypoint for solving the homography estimation problem should have: be repeatable and have a small expected measurement error. This result provides key insights into why maximizing the number of correspondences doesn't always lead to better homography estimation accuracy. We use the developed model to design a method that detects keypoints that benefit the homography estimation introducing the Bounded NeSS-ST (BoNeSS-ST) keypoint detector. The novelty of BoNeSS-ST comes from strong theoretical foundations, a more accurate keypoint scoring due to subpixel refinement and a cost designed for superior robustness to low saliency keypoints. As a result, BoNeSS-ST outperforms prior self-supervised local feature detectors in both planar homography and epipolar geometry estimation problems.
Code (1)
Tasks
Homography EstimationSimilar Papers 제목 키워드 기반
Keypoint-Graph-Driven Learning Framework for Object Pose Estimation
Many recent 6D pose estimation methods exploited object 3D models to generate synthetic images for training because labels come for free. However, due to the domain shift of data distributions between real images and…
6D Pose EstimationDomain AdaptationObjectPose EstimationUnsupervised Depth Estimation, 3D Face Rotation and Replacement
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. W…
Depth EstimationTranslationWeakly Supervised Learning of Keypoints for 6D Object Pose Estimation
State-of-the-art approaches for 6D object pose estimation require large amounts of labeled data to train the deep networks. However, the acquisition of 6D object pose annotations is tedious and labor-intensive in large q…
6D Pose Estimation using RGBKeypoint DetectionObjectPose Estimation+1Occlusion-Aware Networks for 3D Human Pose Estimation in Video
Occlusion is a key problem in 3D human pose estimation from a monocular video. To address this problem, we introduce an occlusion-aware deep-learning framework. By employing estimated 2D confidence heatmaps of keypoints …
3D Human Pose EstimationMonocular 3D Human Pose EstimationOptical Flow EstimationPose EstimationVideo-based estimation of pain indicators in dogs
Dog owners are typically capable of recognizing behavioral cues that reveal subjective states of their dogs, such as pain. But automatic recognition of the pain state is very challenging. This paper proposes a novel vide…