René Schuster
YOU?
Author Swipe
Domain-Incremental Semantic Segmentation for Autonomous Driving under Adverse Driving Conditions Open
Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal conditions show a deteriorated performance in unfavorable weathe…
Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation Open
In autonomous driving, environment perception has significantly advanced with the utilization of deep learning techniques for diverse sensors such as cameras, depth sensors, or infrared sensors. The diversity in the sensor stack increases …
AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy Open
The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a promisi…
ShapeAug++: More Realistic Shape Augmentation for Event Data Open
The novel Dynamic Vision Sensors (DVSs) gained a great amount of attention recently as they are superior compared to RGB cameras in terms of latency, dynamic range and energy consumption. This is particularly of interest for autonomous app…
CLEO: Continual Learning of Evolving Ontologies Open
Continual learning (CL) addresses the problem of catastrophic forgetting in neural networks, which occurs when a trained model tends to overwrite previously learned information, when presented with a new task. CL aims to instill the lifelo…
EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support Open
Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable…
RMS-FlowNet++: Efficient and Robust Multi-scale Scene Flow Estimation for Large-Scale Point Clouds Open
The proposed RMS-FlowNet++ is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation that can operate on high-density point clouds. For hierarchical scene flow estimation, existing methods rely on e…
JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation Open
Part-aware panoptic segmentation is a problem of computer vision that aims to provide a semantic understanding of the scene at multiple levels of granularity. More precisely, semantic areas, object instances, and semantic parts are predict…
ShapeAug: Occlusion Augmentation for Event Camera Data Open
Recently, Dynamic Vision Sensors (DVSs) sparked a lot of interest due to their inherent advantages over conventional RGB cameras. These advantages include a low latency, a high dynamic range and a low energy consumption. Nevertheless, the …
Learned Fusion: 3D Object Detection using Calibration-Free Transformer Feature Fusion Open
The state of the art in 3D object detection using sensor fusion heavily relies on calibration quality, which is difficult to maintain in large scale deployment outside a lab environment. We present the first calibration-free approach for 3…
JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation Open
Part-aware panoptic segmentation is a problem of computer vision that aims to provide a semantic understanding of the scene at multiple levels of granularity. More precisely, semantic areas, object instances, and semantic parts are predict…
Multi-task Fusion for Efficient Panoptic-Part Segmentation Open
In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows…
Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time Open
Object permanence is the concept that objects do not suddenly disappear in the physical world. Humans understand this concept at young ages and know that another person is still there, even though it is temporarily occluded. Neural network…
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation Open
In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although recent works focused on these issues, existing classifier i…
Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences Open
In recent years, deep neural networks showed their exceeding capabilities in addressing many computer vision tasks including scene flow prediction. However, most of the advances are dependent on the availability of a vast amount of dense p…
RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds Open
The proposed RMS-FlowNet is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation which can operate on point clouds of high density. For hierarchical scene flow estimation, the existing methods dep…
Multi-scale Iterative Residuals for Fast and Scalable Stereo Matching Open
Despite the remarkable progress of deep learning in stereo matching, there exists a gap in accuracy between real-time models and slower state-of-the-art models which are suitable for practical applications. This paper presents an iterative…
HPERL: 3D Human Pose Estimation from RGB and LiDAR Open
In-the-wild human pose estimation has a huge potential for various fields, ranging from animation and action recognition to intention recognition and prediction for autonomous driving. The current state-of-the-art is focused only on RGB an…
SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation Open
Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision. State-of-the-art interpolation of motion fields applies model-based interpolation that makes …
MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow Open
Contrary to the ongoing trend in automotive applications towards usage of more diverse and more sensors, this work tries to solve the complex scene flow problem under a monocular camera setup, i.e. using a single sensor. Towards this end, …
A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions Open
Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…
SSGP: Sparse Spatial Guided Propagation for Robust and Generic\n Interpolation Open
Interpolation of sparse pixel information towards a dense target resolution\nfinds its application across multiple disciplines in computer vision.\nState-of-the-art interpolation of motion fields applies model-based\ninterpolation that mak…
DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDAR Open
Scene flow is the dense 3D reconstruction of motion and geometry of a scene. Most state-of-the-art methods use a pair of stereo images as input for full scene reconstruction. These methods depend a lot on the quality of the RGB images and …