A review of 3D reconstruction methods based on deep learning

3D reconstruction is a technical process that constructs a digital 3D model of a target object from low-dimensional data. It plays an important role in medical imaging, cultural relics protection and other fields.Traditional 3D reconstruction techniques suffer from challenges such as difficult feature extraction and heavy manual intervention. Therefore, deep learning has been introduced into this field. After extensive literature review, this paper systematically summarizes classic 3D reconstruction algorithms using deep learning methods, categorizing them into explicit and implicit representation approaches. As cutting-edge technologies in 3D reconstruction, Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) hold significant promise. This paper briefly introduces the fundamental principles and recent advancements of dynamic scenes, outlines commonly used dynamic scene datasets and performance metrics, and compares their performance on the D-NeRF datasets. It concludes by summarizing the main challenges in 3D reconstruction and looks ahead to future developments in technology integration and reducing memory costs for large-scale scenes.