12 citations · 12 across the 2 of their papers we have counts for
6 papers · 1 filter
NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models
Francesco Milano, Jen Jen Chung, Hermann Blum +2
State-of-the-art approaches for 6D object pose estimation assume the availability of CAD models and require the user to manually set up physically-based rendering (PBR) pipelines f…
SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
Robin Chan, Krzysztof Lis, Svenja Uhlemeyer +6
State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle pre…
Pixel-wise Anomaly Detection in Complex Driving Scenes
Giancarlo Di Biase, Hermann Blum, Roland Siegwart +1
The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as au…
This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
David Haldimann, Hermann Blum, Roland Siegwart +1
There has been a remarkable progress in the accuracy of semantic segmentation due to the capabilities of deep learning. Unfortunately, these methods are not able to generalize much…
Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes
Nicolas Marchal, Charlotte Moraldo, Roland Siegwart +3
Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed…
Modular Sensor Fusion for Semantic Segmentation
Hermann Blum, Abel Gawel, Roland Siegwart +1
Sensor fusion is a fundamental process in robotic systems as it extends the perceptual range and increases robustness in real-world operations. Current multi-sensor deep learning b…