Research on unmanned aerial vehicles is growing as they are becoming less expensive
and more available than before. The applications span a large number of areas and include …

Visual simultaneous localization and map** (V-SLAM) plays a crucial role in the field of
robotic systems, especially for interactive and collaborative mobile robots. The growing …

Abstract Neural Radiance Fields (NeRF) have recently gained a surge of interest within the
computer vision community for its power to synthesize photorealistic novel views of real …

Finding local features that are repeatable across multiple views is a cornerstone of sparse
3D reconstruction. The classical image matching paradigm detects keypoints per-image …

A key component of Simultaneous Localization and Map** (SLAM) systems is the joint
optimization of the estimated 3D map and camera trajectory. Bundle adjustment (BA) is the …

Abstract Neural Radiance Fields (NeRF) have achieved photorealistic novel views
synthesis; however, the requirement of accurate camera poses limits its application. Despite …

The ability to predict depth from a single image-using recent advances in CNNs-is of
increasing interest to the vision community. Unsupervised strategies to learning are …

We present RePOSE, a fast iterative refinement method for 6D object pose estimation. Prior
methods perform refinement by feeding zoomed-in input and rendered RGB images into a …

Estimating the pose of a moving camera from monocular video is a challenging problem,
especially due to the presence of moving objects in dynamic environments, where the …

Robust data association is a core problem of visual odometry, where image-to-image
correspondences provide constraints for camera pose and map estimation. Current state-of …