Learning-Based Multi-View Stereo: A Survey.

Journal: IEEE transactions on pattern analysis and machine intelligence
Published Date: Jan 16, 2026

Abstract

3D reconstruction aims to recover the dense 3D structure of a scene. It plays an essential role in various applications such as Augmented/Virtual Reality (AR/VR), autonomous driving and robotics. Leveraging multiple views of a scene captured from different viewpoints, Multi-View Stereo (MVS) algorithms synthesize a comprehensive 3D representation, enabling precise reconstruction in complex environments. Due to its efficiency and effectiveness, MVS has become a pivotal method for image-based 3D reconstruction. Recently, with the success of deep learning, many learning-based MVS methods have been proposed, achieving impressive performance against traditional methods. We categorize these learning-based methods as: depth map-based, voxel-based, NeRF-based, 3D Gaussian Splatting-based, and large feed-forward methods. Among these, we focus significantly on depth map-based methods, which are the main family of MVS due to their conciseness, flexibility and scalability. In this survey, we provide a comprehensive review of the literature at the time of this writing. We investigate these learning-based methods, summarize their performances on popular benchmarks, and discuss promising future research directions in this area.

Authors

  • Fangjinhua Wang
  • Qingtian Zhu
  • Di Chang
    Department of Micro-Nano Mechanical Science and Engineering, Nagoya University, Nagoya, Aichi, Japan. [email protected].
  • Quankai Gao
  • Junlin Han
  • Tong Zhang
    Beijing University of Chinese Medicine, Beijing, China.
  • Richard Hartley
    Australian National University, Canberra, Australia; Data61, CSIRO, Canberra, Australia; Australian Centre for Robotic Vision, Australia.
  • Marc Pollefeys
    Computer Vision and Geometry Group, ETH Zurich, Zurich, Switzerland.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals