TY - GEN
T1 - A Modular Approach for 3D Reconstruction with Point Cloud Overlay
AU - Schieber, Hannah
AU - Schmid, Fritz
AU - Mubashir-Ui-Hassan,
AU - Zollmann, Stefanie
AU - Roth, Daniel
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Integrating the real-world through the power of 3D reconstruction plays an essential role in extended reality teleconsultation. Video streams and voxel-based representations are common techniques for teleconsultation visualization. However, video streaming applications miss 3D content information, and voxel-based representation can only provide visual details with increasing computational costs. To enhance the classical voxel-based representation and address the timeliness of voxels, we present a modular approach which provides a point cloud overlay to highlight the latest update in the current camera frustum. Our approach applies state-of-the-art algorithms and custom packages within ROS to enable 3D reconstruction with dynamic cameras. We present a modular approach allowing the flexible exchange of the individual part, i.e. the camera or SLAM algorithm. This work presents results from a pilot study involving five participants to gain an impression of what kind of visualization type would be preferred and whether the point cloud overlay would assist the user in recognizing changes in the surroundings. The point cloud overlay enabled the participants to perceive more changes. The pilot study revealed that 60% of the participants showed a preference for the point cloud overlay over the pure mesh representation.
AB - Integrating the real-world through the power of 3D reconstruction plays an essential role in extended reality teleconsultation. Video streams and voxel-based representations are common techniques for teleconsultation visualization. However, video streaming applications miss 3D content information, and voxel-based representation can only provide visual details with increasing computational costs. To enhance the classical voxel-based representation and address the timeliness of voxels, we present a modular approach which provides a point cloud overlay to highlight the latest update in the current camera frustum. Our approach applies state-of-the-art algorithms and custom packages within ROS to enable 3D reconstruction with dynamic cameras. We present a modular approach allowing the flexible exchange of the individual part, i.e. the camera or SLAM algorithm. This work presents results from a pilot study involving five participants to gain an impression of what kind of visualization type would be preferred and whether the point cloud overlay would assist the user in recognizing changes in the surroundings. The point cloud overlay enabled the participants to perceive more changes. The pilot study revealed that 60% of the participants showed a preference for the point cloud overlay over the pure mesh representation.
KW - Artificial
KW - I.4.5 [Reconstruction]:
KW - [H.5.1]: Multimedia Information Systems
KW - and virtual realities
KW - augmented
UR - http://www.scopus.com/inward/record.url?scp=85180364232&partnerID=8YFLogxK
U2 - 10.1109/ISMAR-Adjunct60411.2023.00129
DO - 10.1109/ISMAR-Adjunct60411.2023.00129
M3 - Conference contribution
AN - SCOPUS:85180364232
T3 - Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023
SP - 609
EP - 610
BT - Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023
A2 - Bruder, Gerd
A2 - Olivier, Anne-Helene
A2 - Cunningham, Andrew
A2 - Peng, Evan Yifan
A2 - Grubert, Jens
A2 - Williams, Ian
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023
Y2 - 16 October 2023 through 20 October 2023
ER -