IEEE Trans Pattern Anal Mach Intell. 2021 May;43(5):1578-1604. doi: 10.1109/TPAMI.2019.2954885. Epub 2021 Apr 1.
3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural networks (CNN) has attracted increasing interest and demonstrated an impressive performance. Given this new era of rapid evolution, this article provides a comprehensive survey of the recent developments in this field. We focus on the works which use deep learning techniques to estimate the 3D shape of generic objects either from a single or multiple RGB images. We organize the literature based on the shape representations, the network architectures, and the training mechanisms they use. While this survey is intended for methods which reconstruct generic objects, we also review some of the recent works which focus on specific object classes such as human body shapes and faces. We provide an analysis and comparison of the performance of some key papers, summarize some of the open problems in this field, and discuss promising directions for future research.
3D 重建是一个长期存在的不适定问题，已经被计算机视觉、计算机图形学和机器学习领域探索了几十年。自 2015 年以来，使用卷积神经网络（CNN）的基于图像的 3D 重建引起了越来越多的关注，并展示了令人印象深刻的性能。鉴于这一快速发展的新时代，本文对该领域的最新发展进行了全面调查。我们专注于使用深度学习技术从单个或多个 RGB 图像估计通用物体 3D 形状的工作。我们根据形状表示、网络架构以及它们使用的训练机制对文献进行组织。虽然这项调查旨在针对重建通用对象的方法，但我们也回顾了一些最近专注于特定对象类（如人体形状和人脸）的工作。我们对一些关键论文的性能进行了分析和比较，总结了该领域的一些开放性问题，并讨论了未来研究的有前途的方向。
