Three-dimensional mapping is an increasingly important feature for recent photogrammetry
and remote sensing (RS) systems. Currently, unmanned aerial vehicles (UAVs) have …

We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM
consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense …

Generating robust and reliable correspondences across images is a fundamental task for a
diversity of applications. To capture context at both global and local granularity, we propose …

Removing outlier correspondences is one of the critical steps for successful feature-based
point cloud registration. Despite the increasing popularity of introducing deep learning …

In this work we address the problem of finding reliable pixel-level correspondences under
difficult imaging conditions. We propose an approach where a single convolutional neural …

While deep learning has recently achieved great success on multi-view stereo (MVS),
limited training data makes the trained model hard to be generalized to unseen scenarios …

Establishing correspondences between two images requires both local and global spatial
context. Given putative correspondences of feature points in two views, in this paper, we …

We introduce a comprehensive benchmark for local features and robust estimation
algorithms, focusing on the downstream task—the accuracy of the reconstructed camera …

In this work we address the problem of finding reliable pixel-level correspondences under
difficult imaging conditions. We propose an approach where a single convolutional neural …

This work focuses on mitigating two limitations in the joint learning of local feature detectors
and descriptors. First, the ability to estimate the local shape (scale, orientation, etc.) of …