Zobrazeno 1 - 10
of 230
pro vyhledávání: '"Dai, Dengxin"'
The progress on Hyperspectral image (HSI) super-resolution (SR) is still lagging behind the research of RGB image SR. HSIs usually have a high number of spectral bands, so accurately modeling spectral band interaction for HSI SR is hard. Also, traini
Externí odkaz:
http://arxiv.org/abs/2409.08667
Autor:
Yang, Linyan, Hoyer, Lukas, Weber, Mark, Fischer, Tobias, Dai, Dengxin, Leal-Taixé, Laura, Pollefeys, Marc, Cremers, Daniel, Van Gool, Luc
Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain, e.g., synthetic data, and an unlabeled target domain. We observe that current UDA methods show inferior results on fine structures and tend t
Externí odkaz:
http://arxiv.org/abs/2408.16478
Semi-supervised learning (SSL) methods effectively leverage unlabeled data to improve model generalization. However, SSL models often underperform in open-set scenarios, where unlabeled data contain outliers from novel categories that do not appear i
Externí odkaz:
http://arxiv.org/abs/2311.10572
Autor:
Li, Lei, Liniger, Alexander, Millhaeusler, Mario, Tsiminaki, Vagia, Li, Yuanyou, Dai, Dengxin
Event cameras are gaining popularity due to their unique properties, such as their low latency and high dynamic range. One task where these benefits can be crucial is real-time object detection. However, RGB detectors still outperform event-based det
Externí odkaz:
http://arxiv.org/abs/2311.05494
Autor:
Camiletto, Andrea Boscolo, Bochicchio, Alfredo, Liniger, Alexander, Dai, Dengxin, Gawel, Abel
Efficient relocalization is essential for intelligent vehicles when GPS reception is insufficient or sensor-based localization fails. Recent advances in Bird's-Eye-View (BEV) segmentation allow for accurate estimation of local scene appearance and in
Externí odkaz:
http://arxiv.org/abs/2310.13766
While LiDAR data acquisition is easy, labeling for semantic segmentation remains highly time consuming and must therefore be done selectively. Active learning (AL) provides a solution that can iteratively and intelligently label a dataset while retai
Externí odkaz:
http://arxiv.org/abs/2309.13276
Depth estimation is one of the essential tasks to be addressed when creating mobile autonomous systems. While monocular depth estimation methods have improved in recent times, depth completion provides more accurate and reliable depth maps by additio
Externí odkaz:
http://arxiv.org/abs/2307.12761
Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions. However, this task is challenging due to the diverse behaviors of traffic participants and complex environmental contexts
Externí odkaz:
http://arxiv.org/abs/2306.17770
Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test data might come from a different domain than training data. Therefore, it
Externí odkaz:
http://arxiv.org/abs/2305.13031
Instance segmentation of point clouds is a crucial task in 3D field with numerous applications that involve localizing and segmenting objects in a scene. However, achieving satisfactory results requires a large number of manual annotations, which is
Externí odkaz:
http://arxiv.org/abs/2305.06973