Zobrazeno 61 - 70
of 464
pro vyhledávání: '"Stricker, Didier"'
This paper presents a semantic planar SLAM system that improves pose estimation and mapping using cues from an instance planar segmentation network. While the mainstream approaches are using RGB-D sensors, employing a monocular camera with such a sys
Externí odkaz:
http://arxiv.org/abs/2108.04281
Eye contact between individuals is particularly important for understanding human behaviour. To further investigate the importance of eye contact in social interactions, portable eye tracking technology seems to be a natural choice. However, the anal
Externí odkaz:
http://arxiv.org/abs/2107.04476
Virtual Reality applications are becoming increasingly mature. The requirements and complexity of such systems is steadily increasing. Realistic and detailed environments are often omitted in order to concentrate on the interaction possibilities with
Externí odkaz:
http://arxiv.org/abs/2107.03823
When designing 3D applications it is necessary to find a compromise between cost (e.g. money, time) and achievable realism of the virtual environment. Reusing existing assets has an impact on the uniqueness of the application and creating high qualit
Externí odkaz:
http://arxiv.org/abs/2107.03833
Autor:
Malik, Jameel, Shimada, Soshi, Elhayek, Ahmed, Ali, Sk Aziz, Theobalt, Christian, Golyanik, Vladislav, Stricker, Didier
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. Existing methods addressing it directly regress hand meshes via 2D convolutional neural networks, which leads to artefa
Externí odkaz:
http://arxiv.org/abs/2107.01205
The ability to create an accurate three-dimensional reconstruction of a captured scene draws attention to the principles of light fields. This paper presents an approach for light field camera calibration and rectification, based on pairwise pattern-
Externí odkaz:
http://arxiv.org/abs/2106.06181
Autor:
Stricker, Didier
Im Rahmen dieser Arbeit werden Computer-Vision Methoden zur Lösung der Augmented-Reality Kalibrierungs- und Trackingprobleme entwickelt. Insbesondere wurden (1) neben der ``structure and motion'' Methode, die theoretischen Grundlagen eines neuen Ver
Externí odkaz:
https://tuprints.ulb.tu-darmstadt.de/288/1/stricker_diss.pdf
Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the criterion of
Externí odkaz:
http://arxiv.org/abs/2105.03164
Autor:
Hashmi, Khurram Azeem, Liwicki, Marcus, Stricker, Didier, Afzal, Muhammad Adnan, Afzal, Muhammad Ahtsham, Afzal, Muhammad Zeshan
The first phase of table recognition is to detect the tabular area in a document. Subsequently, the tabular structures are recognized in the second phase in order to extract information from the respective cells. Table detection and structural recogn
Externí odkaz:
http://arxiv.org/abs/2104.14272
Autor:
Hashmi, Khurram Azeem, Stricker, Didier, Liwicki, Marcus, Afzal, Muhammad Noman, Afzal, Muhammad Zeshan
This paper presents the novel approach towards table structure recognition by leveraging the guided anchors. The concept differs from current state-of-the-art approaches for table structure recognition that naively apply object detection methods. In
Externí odkaz:
http://arxiv.org/abs/2104.10538