Segmenting and determining the 3D bounding boxes of objects of interest in RGB videos is an important task for a variety of applications such as augmented reality, navigation, and …
L Kästner, D Dimitrov… - 2020 17th International …, 2020 - ieeexplore.ieee.org
Augmented Reality has been subject to various integration efforts within industries due to its ability to enhance human machine interaction and understanding. Neural networks have …
We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a collection of oriented object bounding boxes (or BB) and their semantic labels. The critical …
L Jiang, S Shi, B Schiele - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
In dynamic 3D environments the ability to recognize a diverse range of objects without the constraints of predefined categories is indispensable for real-world applications. In response …
Y Liao, J Xie, A Geiger - IEEE Transactions on Pattern Analysis …, 2022 - ieeexplore.ieee.org
For the last few decades, several major subfields of artificial intelligence including computer vision, graphics, and robotics have progressed largely independently from each other …
Recently, progress in acquisition equipment such as LiDAR sensors has enabled sensing increasingly spacious outdoor 3D environments. Making sense of such 3D acquisitions …
A Venkataraman, B Griffin, JJ Corso - arXiv preprint arXiv:1901.05580, 2019 - arxiv.org
To be useful in everyday environments, robots must be able to observe and learn about objects. Recent datasets enable progress for classifying data into known object categories; …
J Hou, B Graham, M Nießner… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (eg point clouds) are notoriously hard. For …
Deep neural networks have revolutionized many areas of computer vision, but they require notoriously large amounts of labeled training data. For tasks such as semantic segmentation …