652 citations · 7k across the 163 of their papers we have counts for
31 papers · 1 filter
Local and Global Information in Obstacle Detection on Railway Tracks
Matthias Brucker, Andrei Cramariuc, Cornelius von Einem +2
Reliable obstacle detection on railways could help prevent collisions that result in injuries and potentially damage or derail the train. Unfortunately, generic object detectors do…
Unsupervised Continual Semantic Adaptation through Neural Rendering
Zhizheng Liu, Francesco Milano, Jonas Frey +3
An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deploym…
Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps
Kenneth Blomqvist, Lionel Ott, Jen Jen Chung +1
Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels.…
Semi-automatic 3D Object Keypoint Annotation and Detection for the Masses
Kenneth Blomqvist, Jen Jen Chung, Lionel Ott +1
Creating computer vision datasets requires careful planning and lots of time and effort. In robotics research, we often have to use standardized objects, such as the YCB object set…
NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping
Stefan Lionar, Lukas Schmid, Cesar Cadena +2
We present a novel 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction. Most existing state-of-the-art neural implicit represen…
See Yourself in Others: Attending Multiple Tasks for Own Failure Detection
Boyang Sun, Jiaxu Xing, Hermann Blum +2
Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth esti…
Superquadric Object Representation for Optimization-based Semantic SLAM
Florian Tschopp, Juan Nieto, Roland Siegwart +1
Introducing semantically meaningful objects to visual Simultaneous Localization And Mapping (SLAM) has the potential to improve both the accuracy and reliability of pose estimates,…
Fast Image-Anomaly Mitigation for Autonomous Mobile Robots
Gianmario Fumagalli, Yannick Huber, Marcin Dymczyk +2
Camera anomalies like rain or dust can severelydegrade image quality and its related tasks, such as localizationand segmentation. In this work we address this importantissue by imp…
TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction
Margarita Grinvald, Federico Tombari, Roland Siegwart +1
The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction…
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…
SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)
Timo Hinzmann, Roland Siegwart
This paper introduces SD-6DoF-ICLK, a learning-based Inverse Compositional Lucas-Kanade (ICLK) pipeline that uses sparse depth information to optimize the relative pose that best a…
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…
Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds
Joël Bachmann, Kenneth Blomqvist, Julian Förster +1
Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation…
3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer
Mattia Segu, Margarita Grinvald, Roland Siegwart +1
Transferring the style from one image onto another is a popular and widely studied task in computer vision. Yet, style transfer in the 3D setting remains a largely unexplored probl…
Out-of-Distribution Detection for Automotive Perception
Julia Nitsch, Masha Itkina, Ransalu Senanayake +5
Neural networks (NNs) are widely used for object classification in autonomous driving. However, NNs can fail on input data not well represented by the training dataset, known as ou…
LCD -- Line Clustering and Description for Place Recognition
Felix Taubner, Florian Tschopp, Tonci Novkovic +2
Current research on visual place recognition mostly focuses on aggregating local visual features of an image into a single vector representation. Therefore, high-level information…
Deep UAV Localization with Reference View Rendering
Timo Hinzmann, Roland Siegwart
This paper presents a framework for the localization of Unmanned Aerial Vehicles (UAVs) in unstructured environments with the help of deep learning. A real-time rendering engine is…
Deep Learning-based Human Detection for UAVs with Optical and Infrared Cameras: System and Experiments
Timo Hinzmann, Tobias Stegemann, Cesar Cadena +1
In this paper, we present our deep learning-based human detection system that uses optical (RGB) and long-wave infrared (LWIR) cameras to detect, track, localize, and re-identify h…
Depth Based Semantic Scene Completion with Position Importance Aware Loss
Yu Liu, Jie Li, Xia Yuan +4
Semantic Scene Completion (SSC) refers to the task of inferring the 3D semantic segmentation of a scene while simultaneously completing the 3D shapes. We propose PALNet, a novel hy…
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…
Large-scale, real-time visual-inertial localization revisited
Simon Lynen, Bernhard Zeisl, Dror Aiger +5
The overarching goals in image-based localization are scale, robustness and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both do…
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
Hermann Blum, Paul-Edouard Sarlin, Juan Nieto +2
Deep learning has enabled impressive progress in the accuracy of semantic segmentation. Yet, the ability to estimate uncertainty and detect failure is key for safety-critical appli…
From Coarse to Fine: Robust Hierarchical Localization at Large Scale
Paul-Edouard Sarlin, Cesar Cadena, Roland Siegwart +1
Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augmented reality. It remains, howeve…