We propose a novel framework for finding correspondences in images based on a deep
neural network that, given two images and a query point in one of them, finds its …

This paper introduces SuperGlue, a neural network that matches two sets of local features
by jointly finding correspondences and rejecting non-matchable points. Assignments are …

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

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 …

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 …

The classical matching pipeline used for visual localization typically involves three steps:(i)
local feature detection and description,(ii) feature matching, and (iii) outlier rejection …

3D reconstruction is a long-standing research topic in the photogrammetric and computer
vision communities; although a plethora of open-source and commercial solutions for 3D …

Local feature frameworks are difficult to learn in an end-to-end fashion due to the
discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK …

Semantic 2D maps are commonly used by humans and machines for navigation purposes,
whether it's walking or driving. However, these maps have limitations: they lack detail, often …

Multi-viewpoint image stitching aims to stitch images taken from different viewpoints into
pictures with a broader field of view. The stitched images are subject to artifacts, geometric …