Garnet: Global-aware multi-view 3d reconstruction network and the cost-performance tradeoff

Z Zhu, L Yang, X Lin, L Yang, Y Liang - Pattern Recognition, 2023 - Elsevier
Deep learning technology has made great progress in multi-view 3D reconstruction tasks. At
present, the mainstream solutions adopt different ways to fusion the features from several …

Umiformer: Mining the correlations between similar tokens for multi-view 3d reconstruction

Z Zhu, L Yang, N Li, C Jiang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In recent years, many video tasks have achieved breakthroughs by utilizing the vision
transformer and establishing spatial-temporal decoupling for feature extraction. Although …

TMSDNet: Transformer with multi‐scale dense network for single and multi‐view 3D reconstruction

X Zhu, X Yao, J Zhang, M Zhu, L You… - … and Virtual Worlds, 2024 - Wiley Online Library
Abstract 3D reconstruction is a long‐standing problem. Recently, a number of studies have
emerged that utilize transformers for 3D reconstruction, and these approaches have …

Multi-view 3D reconstruction based on deep learning: A survey and comparison of methods

J Wu, O Wyman, Y Tang, D Pasini, W Wang - Neurocomputing, 2024 - Elsevier
An important objective in computer vision is to analyze multiple images and subsequently
reconstruct the shape and structure in 3D. Traditional multi-view 3D reconstruction …

From a visual scene to a virtual representation: a cross-domain review

A Pereira, P Carvalho, N Pereira, P Viana… - IEEE …, 2023 - ieeexplore.ieee.org
The widespread use of smartphones and other low-cost equipment as recording devices,
the massive growth in bandwidth, and the ever-growing demand for new applications with …

A Coarse-to-Fine Transformer-Based Network for 3D Reconstruction from Non-Overlapping Multi-View Images

Y Shan, J Xiao, L Liu, Y Wang, D Yu, W Zhang - Remote Sensing, 2024 - mdpi.com
Reconstructing 3D structures from non-overlapping multi-view images is a crucial task in the
field of 3D computer vision, since it is difficult to establish feature correspondences and infer …

ED2IF2-Net: Learning Disentangled Deformed Implicit Fields and Enhanced Displacement Fields from Single Images Using Pyramid Vision Transformer

X Zhu, X Yao, J Zhang, M Zhu, L You, X Yang… - Applied Sciences, 2023 - mdpi.com
There has emerged substantial research in addressing single-view 3D reconstruction and
the majority of the state-of-the-art implicit methods employ CNNs as the backbone network …

Toward Cooperative 3D Object Reconstruction with Multi-agent

X Li, Z Wen, L Zhou, C Li, Y Zhou, T Li… - … on Robotics and …, 2023 - ieeexplore.ieee.org
We study the problem of object reconstruction in a multi-agent collaboration scenario.
Specifically, we focus on the reconstruction of specific goals through several cooperative …

Shape2. 5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation

MSU Khan, MZ Afzal, D Stricker - arXiv preprint arXiv:2406.15831, 2024 - arxiv.org
Reconstructing texture-less surfaces poses unique challenges in computer vision, primarily
due to the lack of specialized datasets that cater to the nuanced needs of depth and normals …

3D-COCO: extension of MS-COCO dataset for image detection and 3D reconstruction modules

M Bideaux, A Phe, M Chaouch, B Luvison… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce 3D-COCO, an extension of the original MS-COCO dataset providing 3D
models and 2D-3D alignment annotations. 3D-COCO was designed to achieve computer …