RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds m[......] 继续阅读 >>...
StickyPillars: Robust and Efficient Feature Matching on Point Clouds Using Graph Neural Networks
Robust point cloud registration in real-time is an important prerequisite for many mapping and localization algorithms. Traditional methods like ICP[......] 继续阅读 >>...
Online Invariance Selection for Local Feature Descriptors
To be invariant, or not to be invariant: that is the question formulated in this work about local descriptors. A limitation of current feature descrip[......]...
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the[......] 继续阅读 >>...
From Coarse to Fine: Robust Hierarchical Localization at Large Scale
Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augment[......] 继续阅读 >>...
UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor
It is hard to create consistent ground truth data for interest points in natural images, since interest points are hard to define clearly and consiste[......]...
BA-Net: Dense Bundle Adjustment Network
This paper introduces a network architecture to solve the structure-from-motion (SfM) problem via feature-metric bundle adjustment (BA), which explici[......] 继续阅读 >>...
Learning Less is More – 6D Camera Localization via 3D Surface Regression
Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address the task of...
Deep ChArUco: Dark ChArUco Marker Pose Estimation
ChArUco boards are used for camera calibration, monocular pose estimation, and pose verification in both robotics and augmented reality. Such fiducial[......] 继续阅读 >>...
Deep Closest Point: Learning Representations for Point Cloud Registration
Point cloud registration is a key problem for computer vision applied to robotics, medical imaging, and other applications. This problem involves find[......] 继续阅读 >>...