Eckehard Steinbach
YOU?
Author Swipe
View article: BIR-Adapter: A Low-Complexity Diffusion Model Adapter for Blind Image Restoration
BIR-Adapter: A Low-Complexity Diffusion Model Adapter for Blind Image Restoration Open
This paper introduces BIR-Adapter, a low-complexity blind image restoration adapter for diffusion models. The BIR-Adapter enables the utilization of the prior of pre-trained large-scale diffusion models on blind image restoration without t…
View article: Touch-Augmented Gaussian Splatting for Enhanced 3D Scene Reconstruction
Touch-Augmented Gaussian Splatting for Enhanced 3D Scene Reconstruction Open
This paper presents a multimodal framework that integrates touch signals (contact points and surface normals) into 3D Gaussian Splatting (3DGS). Our approach enhances scene reconstruction, particularly under challenging conditions like low…
View article: Technical Report for Egocentric Mistake Detection for the HoloAssist Challenge
Technical Report for Egocentric Mistake Detection for the HoloAssist Challenge Open
In this report, we address the task of online mistake detection, which is vital in domains like industrial automation and education, where real-time video analysis allows human operators to correct errors as they occur. While previous work…
View article: Proactive robot task sequencing through real-time hand motion prediction in human–robot collaboration
Proactive robot task sequencing through real-time hand motion prediction in human–robot collaboration Open
Human-robot collaboration (HRC) is essential for improving productivity and safety across various industries. While reactive motion re-planning strategies are useful, there is a growing demand for proactive methods that predict human inten…
View article: FARE: A Deep Learning-Based Framework for Radar-based Face Recognition and Out-of-distribution Detection
FARE: A Deep Learning-Based Framework for Radar-based Face Recognition and Out-of-distribution Detection Open
In this work, we propose a novel pipeline for face recognition and out-of-distribution (OOD) detection using short-range FMCW radar. The proposed system utilizes Range-Doppler and micro Range-Doppler Images. The architecture features a pri…
View article: LEMON: Localized Editing With Mesh Optimization and Neural Shaders
LEMON: Localized Editing With Mesh Optimization and Neural Shaders Open
We present LEMON, a mesh editing pipeline that integrates neural deferred shading with localized mesh optimization to enable fast and precise editing of polygonal meshes guided by text prompts. Existing solutions for this problem tend to f…
View article: FERT: Real-Time Facial Expression Recognition with Short-Range FMCW Radar
FERT: Real-Time Facial Expression Recognition with Short-Range FMCW Radar Open
This study proposes a novel approach for real-time facial expression recognition utilizing short-range Frequency-Modulated Continuous-Wave (FMCW) radar equipped with one transmit (Tx), and three receive (Rx) antennas. The system leverages …
View article: LEMON: Localized Editing with Mesh Optimization and Neural Shaders
LEMON: Localized Editing with Mesh Optimization and Neural Shaders Open
In practical use cases, polygonal mesh editing can be faster than generating new ones, but it can still be challenging and time-consuming for users. Existing solutions for this problem tend to focus on a single task, either geometry or nov…
View article: FOOD: Facial Authentication and Out-of-Distribution Detection with Short-Range FMCW Radar
FOOD: Facial Authentication and Out-of-Distribution Detection with Short-Range FMCW Radar Open
This paper proposes a short-range FMCW radar-based facial authentication and out-of-distribution (OOD) detection framework. Our pipeline jointly estimates the correct classes for the in-distribution (ID) samples and detects the OOD samples…
View article: Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression
Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression Open
Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of …
View article: Adapting Learned Image Codecs to Screen Content via Adjustable Transformations
Adapting Learned Image Codecs to Screen Content via Adjustable Transformations Open
As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking b…
View article: ADL4D: Towards A Contextually Rich Dataset for 4D Activities of Daily Living
ADL4D: Towards A Contextually Rich Dataset for 4D Activities of Daily Living Open
Hand-Object Interactions (HOIs) are conditioned on spatial and temporal contexts like surrounding objects, previous actions, and future intents (for example, grasping and handover actions vary greatly based on objects proximity and traject…
View article: HAROOD: Human Activity Classification and Out-of-Distribution Detection with Short-Range FMCW Radar
HAROOD: Human Activity Classification and Out-of-Distribution Detection with Short-Range FMCW Radar Open
We propose HAROOD as a short-range FMCW radar-based human activity classifier and out-of-distribution (OOD) detector. It aims to classify human sitting, standing, and walking activities and to detect any other moving or stationary object a…
View article: OCTOPUS: Optimized Cross-border TeleOperated Medicine Pouring Using NextGen Seamless Communication Networks
OCTOPUS: Optimized Cross-border TeleOperated Medicine Pouring Using NextGen Seamless Communication Networks Open
Teleoperated robotic systems have become instrumental in advancing remote healthcare services, especially in tasks that require precision and expert oversight. The advent of cutting-edge telecommunication infrastructures, such as 5G, has a…
View article: OCTOPUS: Optimized Cross-border TeleOperated Medicine Pouring Using NextGen Seamless Communication Networks
OCTOPUS: Optimized Cross-border TeleOperated Medicine Pouring Using NextGen Seamless Communication Networks Open
Teleoperated robotic systems have become instrumental in advancing remote healthcare services, especially in tasks that require precision and expert oversight. The advent of cutting-edge telecommunication infrastructures, such as 5G, has a…
View article: Enabling Acoustic Audience Feedback in Large Virtual Events
Enabling Acoustic Audience Feedback in Large Virtual Events Open
The COVID-19 pandemic shifted many events in our daily lives into the virtual domain. While virtual conference systems provide an alternative to physical meetings, larger events require a muted audience to avoid an accumulation of backgrou…
View article: Care3D: An Active 3D Object Detection Dataset of Real Robotic-Care Environments
Care3D: An Active 3D Object Detection Dataset of Real Robotic-Care Environments Open
As labor shortage increases in the health sector, the demand for assistive robotics grows. However, the needed test data to develop those robots is scarce, especially for the application of active 3D object detection, where no real data ex…
View article: HOOD: Real-Time Human Presence and Out-of-Distribution Detection Using FMCW Radar
HOOD: Real-Time Human Presence and Out-of-Distribution Detection Using FMCW Radar Open
Detecting human presence indoors with millimeter-wave frequency-modulated continuous-wave (FMCW) radar faces challenges from both moving and stationary clutter. This work proposes a robust and real-time capable human presence and out-of-di…
View article: Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression
Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression Open
Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of …
View article: Remote Task-oriented Grasp Area Teaching By Non-Experts through Interactive Segmentation and Few-Shot Learning
Remote Task-oriented Grasp Area Teaching By Non-Experts through Interactive Segmentation and Few-Shot Learning Open
A robot operating in unstructured environments must be able to discriminate between different grasping styles depending on the prospective manipulation task. Having a system that allows learning from remote non-expert demonstrations can ve…
View article: Large-Scale Collaborative Writing: Technical Challenges and Recommendations
Large-Scale Collaborative Writing: Technical Challenges and Recommendations Open
Collaborative writing is essential for teams that create documents together. Creating documents in large-scale collaborations is a challenging task that requires an efficient workflow. The design of such a workflow has received comparative…
View article: MCROOD: Multi-Class Radar Out-Of-Distribution Detection
MCROOD: Multi-Class Radar Out-Of-Distribution Detection Open
Out-of-distribution (OOD) detection has recently received special attention due to its critical role in safely deploying modern deep learning (DL) architectures. This work proposes a reconstruction-based multi-class OOD detector that opera…
View article: Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar
Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar Open
Out-of-distribution (OOD) detection recently has drawn attention due to its critical role in the safe deployment of modern neural network architectures in real-world applications. The OOD detectors aim to distinguish samples that lie outsi…
View article: Vision-driven Collaborative Mobile Robotic Human Assistant System for Daily Living Activities
Vision-driven Collaborative Mobile Robotic Human Assistant System for Daily Living Activities Open
Assistive robotics is a rapidly growing research area. They are increasingly in demand in industry, medical services, or even domestic environments. Many assistance systems were developed in the last decades to help with industry tasks mai…
View article: Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of Freedom
Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of Freedom Open
The most popular evaluation metric for object detection in 2D images is Intersection over Union (IoU). Existing implementations of the IoU metric for 3D object detection usually neglect one or more degrees of freedom. In this paper, we fir…
View article: Evaluation of Video Coding for Machines without Ground Truth
Evaluation of Video Coding for Machines without Ground Truth Open
In the emerging field of video coding for machines, video datasets with pristine video quality and high-quality annotations are required for a comprehensive evaluation. However, existing video datasets with detailed annotations are severel…