We describe a learning-based system that estimates the camera position and orientation
from a single input image relative to a known environment. The system is flexible wrt the …

We present a simple baseline for directly estimating the relative pose (rotation and
translation, including scale) between two images. Deep methods have recently shown …

Modern deep learning techniques that regress the relative camera pose between two
images have difficulty dealing with challenging scenarios, such as large camera motions …

Symmetric orthogonalization via SVD, and closely related procedures, are well-known
techniques for projecting matrices onto O (n) or SO (n). These tools have long been used for …

Abstract We propose the Model Quality Network, MQ-Net in short, for predicting the quality,
eg the pose error of essential matrices, of models generated inside RANSAC. It replaces the …

3D point cloud registration is fragile to outliers, which are labeled as the points without
corresponding points. To handle this problem, a widely adopted strategy is to estimate the …

Even though considerable progress has been made in deep learning-based 3D point cloud
processing, how to obtain accurate correspondences for robust registration remains a major …

High-dimensional geometric patterns appear in many computer vision problems. In this
work, we present high-dimensional convolutional networks for geometric pattern recognition …

Radar sensors are emerging as solutions for perceiving surroundings and estimating ego-
motion in extreme weather conditions. Unfortunately, radar measurements are noisy and …

CNN-based absolute camera pose estimation methods lack scene generalizability as the
network is trained with scene-specific parameters. In this paper, we aim to solve the scene …