Learning 3d semantic scene graphs from 3d indoor reconstructions

J Wald, H Dhamo, N Navab… - Proceedings of the …, 2020 - openaccess.thecvf.com
Scene understanding has been of high interest in computer vision. It encompasses not only
identifying objects in a scene, but also their relationships within the given context. With this …

Hierarchical multi-view context modelling for 3D object classification and retrieval

AA Liu, H Zhou, W Nie, Z Liu, W Liu, H **e, Z Mao… - Information …, 2021 - Elsevier
Recent advances in 3D sensors and 3D modelling software have led to big 3D data. 3D
object classification and retrieval are becoming important but challenging tasks. One critical …

Learning 3d semantic scene graphs with instance embeddings

J Wald, N Navab, F Tombari - International Journal of Computer Vision, 2022 - Springer
A 3D scene is more than the geometry and classes of the objects it comprises. An essential
aspect beyond object-level perception is the scene context, described as a dense semantic …

FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests

A Abdari, A Falcon, G Serra - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Nowadays, many people frequently have to search for new accommodation options.
Searching for a suitable apartment is a time-consuming process, especially because visiting …

M-GCN: Multi-branch graph convolution network for 2D image-based on 3D model retrieval

WZ Nie, MJ Ren, AA Liu, Z Mao… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
2D image based 3D model retrieval is a challenging research topic in the field of 3D model
retrieval. The huge gap between two modalities-2D image and 3D model, extremely …

Semantic consistency guided instance feature alignment for 2D image-based 3D shape retrieval

H Zhou, W Nie, D Song, N Hu, X Li, AA Liu - Proceedings of the 28th …, 2020 - dl.acm.org
2D image-based 3D shape retrieval (2D-to-3D) investigates the problem of matching the
relevant 3D shapes from gallery dataset when given a query image. Recently, adversarial …

Image-based 3D model retrieval via disentangled feature learning and enhanced semantic alignment

J Nie, T Zhang, T Li, S Yu, X Li, Z Wei - Information Processing & …, 2023 - Elsevier
With the development of 3D technology and the increase in 3D models, 2D image-based 3D
model retrieval tasks have drawn increased attention from scholars. Previous works align …

Smart counting of unboxed stocks in the Warehouse 4.0 ecosystem

V Balaska, D Folinas, FK Konstantinidis… - … on Imaging Systems …, 2022 - ieeexplore.ieee.org
The explosion of logistics is consolidating a positive impact on modern society by offering a
critical contribution to its economic development. Traditional inventory methods tend to be …

Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects

AA Fime, S Mahmud, A Das, MS Islam… - arxiv preprint arxiv …, 2024 - arxiv.org
Automatic scene generation is an essential area of research with applications in robotics,
recreation, visual representation, training and simulation, education, and more. This survey …

Universal cross-domain 3D model retrieval

D Song, TB Li, WH Li, WZ Nie, W Liu… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Recent advances in 3D modeling technologies such as 3D scanning, reconstruction and
printing produce an explosive increasing of 3D models, consequently 3D model …