Work

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

Year: 2021

Type: review

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.

Source: IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI: 10.1109/tpami.2021.3070917

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

Institutions: University of Bologna, Stevens Institute of Technology

Language: English

Topic: Advanced Vision and Imaging

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: RI: Small: Learning to Eliminate Heuristics in Stereo Vision, NRI: Collaborative Research: Autonomous Quadrotors for 3D Modeling and Inspection of Outdoor Infrastructure