Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper.

用于三维重建的深度学习 ，增强,和注册 ： 评论论文。

• 影响指数: 2.738
• 发表时间: 2024 Mar 7
• 来源期刊: Entropy (Basel)
• DOI: 10.3390/e26030235
• PMID: 38539747
• 文章类型: Journal Article
• 中科院分区: Q2
• 作者列表: Vinodkumar PK,Karabulut D,Avots E,Ozcinar C,Anbarjafari G

关键词: 3D augmentation; 3D reconstruction; 3D registration; convolutional neural networks; deep learning; generative adversarial networks; graph neural networks; neural networks; point cloud; review; voxel

Abstract

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future.

摘要

计算机视觉的研究小组，图形,机器学习已经将大量的注意力集中在3D对象重建领域，增强，和注册。深度学习是人工智能中用于解决计算机视觉挑战的主要方法。然而,三维数据的深度学习存在明显的障碍，现在正处于起步阶段。特别是针对三维数据的深度学习取得了重大进展，提供一系列解决这些问题的方法。本研究全面考察了深度学习方法的最新进展。我们检查了许多用于3D对象配准任务的基准模型，增强，和重建。我们彻底分析他们的架构，优势,和约束。总之,本报告全面概述了三维深度学习的最新进展，并强调了未来需要解决的尚未解决的研究领域。