3DRecNet: A 3D Reconstruction Network with Dual Attention and Human-Inspired Memory
Authors: Shoukat, M.A., Sargano, A.B., You, L. and Habib, Z.
Journal: Electronics (Switzerland)
Volume: 13
Issue: 17
eISSN: 2079-9292
DOI: 10.3390/electronics13173391
Abstract:Humans inherently perceive 3D scenes using prior knowledge and visual perception, but 3D reconstruction in computer graphics is challenging due to complex object geometries, noisy backgrounds, and occlusions, leading to high time and space complexity. To addresses these challenges, this study introduces 3DRecNet, a compact 3D reconstruction architecture optimized for both efficiency and accuracy through five key modules. The first module, the Human-Inspired Memory Network (HIMNet), is designed for initial point cloud estimation, assisting in identifying and localizing objects in occluded and complex regions while preserving critical spatial information. Next, separate image and 3D encoders perform feature extraction from input images and initial point clouds. These features are combined using a dual attention-based feature fusion module, which emphasizes features from the image branch over those from the 3D encoding branch. This approach ensures independence from proposals at inference time and filters out irrelevant information, leading to more accurate and detailed reconstructions. Finally, a Decoder Branch transforms the fused features into a 3D representation. The integration of attention-based fusion with the memory network in 3DRecNet significantly enhances the overall reconstruction process. Experimental results on the benchmark datasets, such as ShapeNet, ObjectNet3D, and Pix3D, demonstrate that 3DRecNet outperforms existing methods.
https://eprints.bournemouth.ac.uk/40362/
Source: Scopus
3DRecNet: A 3D Reconstruction Network with Dual Attention and Human-Inspired Memory
Authors: Shoukat, M.A., Sargano, A.B., You, L. and Habib, Z.
Journal: ELECTRONICS
Volume: 13
Issue: 17
eISSN: 2079-9292
DOI: 10.3390/electronics13173391
https://eprints.bournemouth.ac.uk/40362/
Source: Web of Science (Lite)
3DRecNet: A 3D Reconstruction Network with Dual Attention and Human-Inspired Memory
Authors: Shoukat, M.A., Sargano, A.B., You, L. and Habib, Z.
Journal: Electronics
Volume: 13
Issue: 17
ISSN: 2079-9292
Abstract:Humans inherently perceive 3D scenes using prior knowledge and visual perception, but 3D reconstruction in computer graphics is challenging due to complex object geometries, noisy backgrounds, and occlusions, leading to high time and space complexity. To addresses these challenges, this study introduces 3DRecNet, a compact 3D reconstruction architecture optimized for both efficiency and accuracy through five key modules. The first module, the Human-Inspired Memory Network (HIMNet), is designed for initial point cloud estimation, assisting in identifying and localizing objects in occluded and complex regions while preserving critical spatial information. Next, separate image and 3D encoders perform feature extraction from input images and initial point clouds. These features are combined using a dual attention-based feature fusion module, which emphasizes features from the image branch over those from the 3D encoding branch. This approach ensures independence from proposals at inference time and filters out irrelevant information, leading to more accurate and detailed reconstructions. Finally, a Decoder Branch transforms the fused features into a 3D representation. The integration of attention-based fusion with the memory network in 3DRecNet significantly enhances the overall reconstruction process. Experimental results on the benchmark datasets, such as ShapeNet, ObjectNet3D, and Pix3D, demonstrate that 3DRecNet outperforms existing methods.
https://eprints.bournemouth.ac.uk/40362/
Source: BURO EPrints