On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: A Survey

Matteo Poggi, Fabio Tosi, Konstantinos Batsos, Philippos Mordohai, Stefano Mattoccia

Research output: Contribution to journalReview articlepeer-review

92 Scopus citations

Abstract

Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research. Throughout the years the paradigm has shifted from local, pixel-level decision to various forms of discrete and continuous optimization to data-driven, learning-based methods. Recently, the rise of machine learning and the rapid proliferation of deep learning enhanced stereo matching with new exciting trends and applications unthinkable until a few years ago. Interestingly, the relationship between these two worlds is two-way. While machine, and especially deep, learning advanced the state-of-the-art in stereo matching, stereo itself enabled new ground-breaking methodologies such as self-supervised monocular depth estimation based on deep networks. In this paper, we review recent research in the field of learning-based depth estimation from single and binocular images highlighting the synergies, the successes achieved so far and the open challenges the community is going to face in the immediate future.

Original languageEnglish
Pages (from-to)5314-5334
Number of pages21
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume44
Issue number9
DOIs
StatePublished - 1 Sep 2022

Keywords

  • Stereo matching
  • deep learning
  • machine learning
  • monocular depth estimation

Fingerprint

Dive into the research topics of 'On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: A Survey'. Together they form a unique fingerprint.

Cite this