Skip to main content

Augmented Reality Enhanced: 3D Crowd Reconstruction from a Single Viewpoint.

Sun, X. and Yang, X., 2025. Augmented Reality Enhanced: 3D Crowd Reconstruction from a Single Viewpoint. In: 2024 10th International Conference on Virtual Reality (ICVR). New York, NY: IEEE, 140-145.

Full text available as:

[thumbnail of ieee_latex_conference.pdf]
Preview
PDF
ieee_latex_conference.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

9MB

DOI: 10.1109/ICVR62393.2024.10868584

Abstract

Reconstructing human figures from a single view-point has long intrigued researchers, particularly for augmented reality (AR) applications. While significant progress has been made in single-human body reconstruction, densely populated scenes with substantial occlusions pose complex challenges. This paper introduces 3DCrowd+, an advanced two-stage methodology for 3D reconstruction of human meshes in crowded environments. Building on the 3DCrowdNet framework, our model refines HRNet 2D pose estimation and integrates Lite-HRNet with Shuffle Block and CoordAttention modules, achieving robust feature extraction and lightweight performance. 3DCrowd+ combines an attention mechanism with a model pruning algorithm, demonstrating high accuracy and efficiency on various datasets. This research bridges the gap between complex crowd scenes and detailed 3D reconstruction, offering a promising solution for precise crowd modeling in AR environments.

Item Type:Book Section
Additional Information:24-26 July 2024 Bournemouth, United Kingdom
Uncontrolled Keywords:Solid modeling; Three-dimensional displays; Attention mechanisms; Accuracy; Pose estimation; Buildings; Feature extraction; Augmented reality; 3D Reconstruction; Augmented Reality (AR); Crowd Modeling; Pose Estimation; Computer Vision
Group:UNSPECIFIED
ID Code:40859
Deposited By: Symplectic RT2
Deposited On:18 Mar 2025 09:14
Last Modified:18 Mar 2025 09:15

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -