In the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization
and Mapping (visual SLAM) techniques have gained significant interest from both the …

As a fundamental and critical task in various visual applications, image matching can identify
then correspond the same or similar structure/content from two or more images. Over the …

We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …

The past few years have seen an accelerating integration of deep learning (DL) techniques
into various remote sensing (RS) applications, highlighting their power to adapt and …

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 …

Despite being robust to small amounts of label noise, convolutional neural networks trained
with stochastic gradient methods have been shown to easily fit random labels. When there …

Do visual tasks have a relationship, or are they unrelated? For instance, could having
surface normals simplify estimating the depth of an image? Intuition answers these …

Registration for multisensor or multimodal image pairs with a large degree of distortions is a
fundamental task for many remote sensing applications. To achieve accurate and low-cost …

Traditional feature-based image stitching technologies rely heavily on feature detection
quality, often failing to stitch images with few features or low resolution. The learning-based …

This paper presents a self-supervised framework for training interest point detectors and
descriptors suitable for a large number of multiple-view geometry problems in computer …