activity
20192022
most citedEstimating Model Uncertainty of Neural Networks in Sparse Information Form

12 citations · 42 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV20221 cited

Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects

Manuel Stoiber, Martin Sundermeyer, Rudolph Triebel

Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision. State-of-the-art approaches often rely on object texture to tackle this problem…

cs.CV20225 cited

A Model for Multi-View Residual Covariances based on Perspective Deformation

Alejandro Fontan, Laura Oliva, Javier Civera +1

In this work, we derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. The core of our approach is the formulation of the residual…

cs.CV2021

Unknown Object Segmentation from Stereo Images

Maximilian Durner, Wout Boerdijk, Martin Sundermeyer +3

Although instance-aware perception is a key prerequisite for many autonomous robotic applications, most of the methods only partially solve the problem by focusing solely on known…

cs.CV2020

"What's This?" -- Learning to Segment Unknown Objects from Manipulation Sequences

Wout Boerdijk, Martin Sundermeyer, Maximilian Durner +1

We present a novel framework for self-supervised grasped object segmentation with a robotic manipulator. Our method successively learns an agnostic foreground segmentation followed…

cs.CV2020

DOT: Dynamic Object Tracking for Visual SLAM

Irene Ballester, Alejandro Fontan, Javier Civera +2

In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic en…

cs.CV20205 cited

Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry

Kashmira Shinde, Jongseok Lee, Matthias Humt +2

This paper presents an end-to-end multi-modal learning approach for monocular Visual-Inertial Odometry (VIO), which is specifically designed to exploit sensor complementarity in th…