Deep-Learning-Based 3-D Surface Reconstruction-A Survey

Anis Farshian, Markus Gotz, Gabriele Cavallaro, Charlotte Debus, Matthias Niesner, Jon Atli Benediktsson, Achim Streit

Research output: Contribution to journalArticlepeer-review


In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point-and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments.

Original languageEnglish
Pages (from-to)1464-1501
Number of pages38
JournalProceedings of the IEEE
Issue number11
Publication statusPublished - 1 Nov 2023

Bibliographical note

Publisher Copyright:
© 1963-2012 IEEE.

Other keywords

  • 3-D deep learning (DL)
  • 3-D surface reconstruction
  • geometric DL
  • geometry processing
  • machine learning


Dive into the research topics of 'Deep-Learning-Based 3-D Surface Reconstruction-A Survey'. Together they form a unique fingerprint.

Cite this