Daniel Gehrig
YOU?
Author Swipe
View article: Neural Inertial Odometry from Lie Events
Neural Inertial Odometry from Lie Events Open
View article: Neural Inertial Odometry from Lie Events
Neural Inertial Odometry from Lie Events Open
Neural displacement priors (NDP) can reduce the drift in inertial odometry and provide uncertainty estimates that can be readily fused with off-the-shelf filters. However, they fail to generalize to different IMU sampling rates and traject…
View article: ETAP: Event-based Tracking of Any Point
ETAP: Event-based Tracking of Any Point Open
Tracking any point (TAP) recently shifted the motion estimation paradigm from focusing on individual salient points with local templates to tracking arbitrary points with global image contexts. However, while research has mostly focused on…
View article: EqNIO: Subequivariant Neural Inertial Odometry
EqNIO: Subequivariant Neural Inertial Odometry Open
Neural networks are seeing rapid adoption in purely inertial odometry, where accelerometer and gyroscope measurements from commodity inertial measurement units (IMU) are used to regress displacements and associated uncertainties. They can …
View article: Low-latency automotive vision with event cameras
Low-latency automotive vision with event cameras Open
The computer vision algorithms used currently in advanced driver assistance systems rely on image-based RGB cameras, leading to a critical bandwidth–latency trade-off for delivering safe driving experiences. To address this, event cameras …
View article: An N-Point Linear Solver for Line and Motion Estimation with Event Cameras
An N-Point Linear Solver for Line and Motion Estimation with Event Cameras Open
Event cameras respond primarily to edges--formed by strong gradients--and are thus particularly well-suited for line-based motion estimation. Recent work has shown that events generated by a single line each satisfy a polynomial constraint…
View article: E-Calib: A Fast, Robust, and Accurate Calibration Toolbox for Event Cameras
E-Calib: A Fast, Robust, and Accurate Calibration Toolbox for Event Cameras Open
Event cameras triggered a paradigm shift in the computer vision community delineated by their asynchronous nature, low latency, and high dynamic range. Calibration of event cameras is always essential to account for the sensor intrinsic pa…
View article: A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
A 5-Point Minimal Solver for Event Camera Relative Motion Estimation Open
Event-based cameras are ideal for line-based motion estimation, since they predominantly respond to edges in the scene. However, accurately determining the camera displacement based on events continues to be an open problem. This is becaus…
View article: From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection
From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection Open
Today, state-of-the-art deep neural networks that process events first convert them into dense, grid-like input representations before using an off-the-shelf network. However, selecting the appropriate representation for the task tradition…
View article: A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
A 5-Point Minimal Solver for Event Camera Relative Motion Estimation Open
Event-based cameras are ideal for line-based motion estimation, since they predominantly respond to edges in the scene. However, accurately determining the camera displacement based on events continues to be an open problem. This is becaus…
View article: Deep Visual Odometry with Events and Frames
Deep Visual Odometry with Events and Frames Open
Visual Odometry (VO) is crucial for autonomous robotic navigation, especially in GPS-denied environments like planetary terrains. To improve robustness, recent model-based VO systems have begun combining standard and event-based cameras. W…
View article: E-Calib: A Fast, Robust and Accurate Calibration Toolbox for Event Cameras
E-Calib: A Fast, Robust and Accurate Calibration Toolbox for Event Cameras Open
Event cameras triggered a paradigm shift in the computer vision community delineated by their asynchronous nature, low latency, and high dynamic range. Calibration of event cameras is always essential to account for the sensor intrinsic pa…
View article: Event-based Agile Object Catching with a Quadrupedal Robot
Event-based Agile Object Catching with a Quadrupedal Robot Open
Quadrupedal robots are conquering various indoor and outdoor applications due to their ability to navigate challenging uneven terrains. Exteroceptive information greatly enhances this capability since perceiving their surroundings allows t…
View article: From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection
From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection Open
Today, state-of-the-art deep neural networks that process events first convert them into dense, grid-like input representations before using an off-the-shelf network. However, selecting the appropriate representation for the task tradition…
View article: A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception
A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception Open
Spiking Neural Networks (SNN) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge devices through asynchronous and sparse processing. However, being temporal models, SNNs depend hea…
View article: Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras
Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras Open
State-of-the-art machine-learning methods for event cameras treat events as dense representations and process them with conventional deep neural networks. Thus, they fail to maintain the sparsity and asynchronous nature of event data, ther…
View article: Exploring Event Camera-Based Odometry for Planetary Robots
Exploring Event Camera-Based Odometry for Planetary Robots Open
Due to their resilience to motion blur and high robustness in low-light and high dynamic range conditions, event cameras are poised to become enabling sensors for vision-based exploration on future Mars helicopter missions. However, existi…
View article: Time Lens++: Event-based Frame Interpolation with Parametric Nonlinear Flow and Multi-scale Fusion
Time Lens++: Event-based Frame Interpolation with Parametric Nonlinear Flow and Multi-scale Fusion Open
Recently, video frame interpolation using a combination of frame- and event-based cameras has surpassed traditional image-based methods both in terms of performance and memory efficiency. However, current methods still suffer from (i) brit…
View article: Biosynthetic potential of the global ocean microbiome
Biosynthetic potential of the global ocean microbiome Open
View article: Multi-Bracket High Dynamic Range Imaging with Event Cameras
Multi-Bracket High Dynamic Range Imaging with Event Cameras Open
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low dynamic range (LDR) images captured at different exposure times. While these methods work well in static scenes, dynamic scenes remain a challenge since the LDR …
View article: Exploring Event Camera-based Odometry for Planetary Robots
Exploring Event Camera-based Odometry for Planetary Robots Open
Due to their resilience to motion blur and high robustness in low-light and high dynamic range conditions, event cameras are poised to become enabling sensors for vision-based exploration on future Mars helicopter missions. However, existi…
View article: AEGNN: Asynchronous Event-based Graph Neural Networks
AEGNN: Asynchronous Event-based Graph Neural Networks Open
The best performing learning algorithms devised for event cameras work by first converting events into dense representations that are then processed using standard CNNs. However, these steps discard both the sparsity and high temporal reso…
View article: Are High-Resolution Event Cameras Really Needed?
Are High-Resolution Event Cameras Really Needed? Open
Due to their outstanding properties in challenging conditions, event cameras have become indispensable in a wide range of applications, ranging from automotive, computational photography, and SLAM. However, as further improvements are made…
View article: Multi-Bracket High Dynamic Range Imaging with Event Cameras
Multi-Bracket High Dynamic Range Imaging with Event Cameras Open
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low dynamic range (LDR) images captured at different exposure times. While these methods work well in static scenes, dynamic scenes remain a challenge since the LDR …
View article: Bridging the Gap Between Events and Frames Through Unsupervised Domain Adaptation
Bridging the Gap Between Events and Frames Through Unsupervised Domain Adaptation Open
Reliable perception during fast motion maneuvers or in high dynamic range\nenvironments is crucial for robotic systems. Since event cameras are robust to\nthese challenging conditions, they have great potential to increase the\nreliability…
View article: Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction Open
Event cameras are novel vision sensors that report per-pixel brightness changes as a stream of asynchronous "events". They offer significant advantages compared to standard cameras due to their high temporal resolution, high dynamic range …
View article: ESS: Learning Event-Based Semantic Segmentation from Still Images
ESS: Learning Event-Based Semantic Segmentation from Still Images Open
View article: E-RAFT: Dense Optical Flow from Event Cameras
E-RAFT: Dense Optical Flow from Event Cameras Open
We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely on matching costs computed from feature correlation. In con…
View article: Conjugative plasmid transfer is limited by prophages but can be overcome by high conjugation rates
Conjugative plasmid transfer is limited by prophages but can be overcome by high conjugation rates Open
Antibiotic resistance spread via plasmids is a serious threat to successfully fight infections and makes understanding plasmid transfer in nature crucial to prevent the rise of antibiotic resistance. Studies addressing the dynamics of plas…
View article: Dense Optical Flow from Event Cameras.
Dense Optical Flow from Event Cameras. Open
We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely on matching costs computed from feature correlation. In con…