Niko Sunderhauf — accepted AI-conference papers

2025

Multi-View Pose-Agnostic Change Localization with Zero Labels

Chamuditha Jayanga Galappaththige, Jason Lai, Lloyd Windrim, Donald Dansereau, Niko Sunderhauf, Dimity Miller

CVPR 2025poster

Autonomous agents often require accurate methods for detecting and localizing changes in their environment, particularly when observations are captured from unconstrained and inconsistent viewpoints. We propose a novel label-free, pose-agnostic change detection method that integrates information fro…

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

VarifocalNet: An IoU-Aware Dense Object Detector

Haoyang Zhang, Ying Wang, Feras Dayoub, Niko Sunderhauf

CVPR 2021poster

Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliabl…

Cited by 1075 PDF ↗code ↗Scholar ↗

2018

Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal

Jake Bruce, Niko Sunderhauf, Piotr Mirowski, Raia Hadsell, Michael Milford

CoRL 2018

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be prohibitively costly to obtain on robots in the real world. We

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗