Zobrazeno 21 - 30
of 464
pro vyhledávání: '"Stricker, Didier"'
3D reconstruction of hand-object manipulations is important for emulating human actions. Most methods dealing with challenging object manipulation scenarios, focus on hands reconstruction in isolation, ignoring physical and kinematic constraints due
Externí odkaz:
http://arxiv.org/abs/2310.11811
By exploiting complementary sensor information, radar and camera fusion systems have the potential to provide a highly robust and reliable perception system for advanced driver assistance systems and automated driving functions. Recent advances in ca
Externí odkaz:
http://arxiv.org/abs/2309.15465
Autor:
Khan, Muhammad Gul Zain Ali, Naeem, Muhammad Ferjad, Van Gool, Luc, Stricker, Didier, Tombari, Federico, Afzal, Muhammad Zeshan
Continual Learning aims to learn a single model on a sequence of tasks without having access to data from previous tasks. The biggest challenge in the domain still remains catastrophic forgetting: a loss in performance on seen classes of earlier task
Externí odkaz:
http://arxiv.org/abs/2308.15827
Many medical or pharmaceutical processes have strict guidelines regarding continuous hygiene monitoring. This often involves the labor-intensive task of manually counting microorganisms in Petri dishes by trained personnel. Automation attempts often
Externí odkaz:
http://arxiv.org/abs/2308.09436
Accurate, robust, and real-time LiDAR-based odometry (LO) is imperative for many applications like robot navigation, globally consistent 3D scene map reconstruction, or safe motion-planning. Though LiDAR sensor is known for its precise range measurem
Externí odkaz:
http://arxiv.org/abs/2308.07153
Autor:
Di, Yan, Zhang, Chenyangguang, Zhang, Ruida, Manhardt, Fabian, Su, Yongzhi, Rambach, Jason, Stricker, Didier, Ji, Xiangyang, Tombari, Federico
In this paper, we propose U-RED, an Unsupervised shape REtrieval and Deformation pipeline that takes an arbitrary object observation as input, typically captured by RGB images or scans, and jointly retrieves and deforms the geometrically similar CAD
Externí odkaz:
http://arxiv.org/abs/2308.06383
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision
Extracting useful visual cues for the downstream tasks is especially challenging under low-light vision. Prior works create enhanced representations by either correlating visual quality with machine perception or designing illumination-degrading tran
Externí odkaz:
http://arxiv.org/abs/2308.03594
While transformer architectures have dominated computer vision in recent years, these models cannot easily be deployed on hardware with limited resources for autonomous driving tasks that require real-time-performance. Their computational complexity
Externí odkaz:
http://arxiv.org/abs/2307.09120
Autor:
Sharma, Pranav, Katrolia, Jigyasa Singh, Rambach, Jason, Mirbach, Bruno, Stricker, Didier, Seiler, Juergen
Depth is a very important modality in computer vision, typically used as complementary information to RGB, provided by RGB-D cameras. In this work, we show that it is possible to obtain the same level of accuracy as RGB-D cameras on a semantic segmen
Externí odkaz:
http://arxiv.org/abs/2306.17636
Autor:
Shehzadi, Tahira, Hashmi, Khurram Azeem, Stricker, Didier, Liwicki, Marcus, Afzal, Muhammad Zeshan
This paper takes an important step in bridging the performance gap between DETR and R-CNN for graphical object detection. Existing graphical object detection approaches have enjoyed recent enhancements in CNN-based object detection methods, achieving
Externí odkaz:
http://arxiv.org/abs/2306.13526