Year: 2024
Type: editorial
Abstract: This special issue consists of two papers selected from the DAGM GCPR conference (German Conference on Pattern Recognition) held in Konstanz, Germany, September 27-30, 2022 jointly with VMV (Vision, Modeling and Visualizaition).It was the 44th edition of an international conference series organized by DAGM (The German Association for Pattern Recognition), which was run under the name DAGM Symposium for Pattern Recognition until 2012 und German Conference on Pattern Recognition afterwards.A selection of four papers ranked highest by an evaluation committee during the conference were invited by us, the program chairs of DAGM GCPR 2022, to submit extended manuscripts to this special issue.We received three submissions, which underwent an additional rigorous peer-review process according to the journal's high standards, and two were finally accepted for this special issue.The first article, by Yinghao Huang, Omid Taheri, Michael J. Black, and Dimitrios Tzionas addresses the challenge of reconstructing 3D interactions between humans and objects from images.They introduce and adress limitations of Inter-Cap, a novel method that uses multi-view RGB-D data and the SMPL-X model to reconstruct whole-body and object interactions.InterCap leverages contact points between the body and objects to improve pose estimation and uses Azure Kinect cameras to reduce occlusions.They further use their method to capture a dataset with 10 subjects interacting with various objects, including contact with hands and feet.Inter-Cap fills a significant gap in the literature and supports diverse research avenues, with data and code available online.
Author: Bastian Goldluecke
Institution: University of Konstanz
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,890
Funder: Universität Konstanz
OpenAlex ID: W4402711326