“Temporal Hierarchical Gaussian Mixture Models for Real-Time Point Cloud Streaming” by Fischer, Gels, Weller and Zachmann
Conference:
Type(s):
Title:
- Temporal Hierarchical Gaussian Mixture Models for Real-Time Point Cloud Streaming
Session/Category Title: Geometry & Modeling
Presenter(s)/Author(s):
Abstract:
We propose a novel approach for point cloud streaming consisting of a methodology that constructs a hierarchy of GMMs. This allows for a compact footprint and dynamic, progressive transmission and rendering of LODs. We achieve real-time and high-fidelity reconstructions by exploiting temporal coherence and a highly parallelized CUDA implementation.
References:
[1]
Ben Eckart, Kihwan Kim, Alejandro Troccoli, Alonzo Kelly, and Jan Kautz. 2016. Accelerated Generative Models for 3D Point Cloud Data. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5497?5505.
[2]
Kshitij Goel and Wennie Tabib. 2023. Incremental Multimodal Surface Mapping via Self-Organizing Gaussian Mixture Models. IEEE Robotics and Automation Letters PP (12 2023), 1?8.
[3]
John R. Hershey and Peder A. Olsen. 2007. Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing – ICASSP ?07, Vol. 4. IV?317?IV?320.
[4]
Kevin Yu, Gleb Gorbachev, Ulrich Eck, Frieder Pankratz, Nassir Navab, and Daniel Roth. 2021. Avatars for Teleconsultation: Effects of Avatar Embodiment Techniques on User Perception in 3D Asymmetric Telepresence. IEEE Transactions on Visualization and Computer Graphics PP (08 2021), 1?1.
