Staff Profile Pages

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

Authors: Sun, X. and Yang, X.

Journal: 2024 10th International Conference on Virtual Reality, ICVR 2024

Pages: 140-145

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.

https://eprints.bournemouth.ac.uk/40859/

Source: Scopus

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

Authors: Sun, X. and Yang, X.

Pages: 140-145

Publisher: IEEE

Place of Publication: New York, NY

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.

https://eprints.bournemouth.ac.uk/40859/

Source: BURO EPrints