A Survey on Deep Stereo Matching in the Twenties

TL;DR

This survey comprehensively reviews recent advancements in deep stereo matching during the 2020s, highlighting architectural innovations and critical challenges, and provides a taxonomy and analysis of state-of-the-art techniques.

Contribution

It offers an in-depth analysis of the latest deep stereo matching architectures and challenges, filling a gap left by earlier surveys and guiding future research directions.

Findings

Detailed taxonomy of challenges in deep stereo matching

Analysis of recent architectural innovations

Identification of key research gaps

Abstract

Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in the last decade thanks to deep learning. While previous surveys in the late 2010s covered the first stage of this revolution, the last five years of research brought further ground-breaking advancements to the field. This paper aims to fill this gap in a two-fold manner: first, we offer an in-depth examination of the latest developments in deep stereo matching, focusing on the pioneering architectural designs and groundbreaking paradigms that have redefined the field in the 2020s; second, we present a thorough analysis of the critical challenges that have emerged alongside these advances, providing a comprehensive taxonomy of these issues and exploring the state-of-the-art techniques proposed to address them. By reviewing both the architectural innovations and the key challenges, we offer a holistic view of deep stereo matching and highlight the specific areas that require further investigation. To accompany this survey, we maintain a regularly updated project page that catalogs papers on deep stereo matching in our Awesome-Deep-Stereo-Matching (https://github.com/fabiotosi92/Awesome-Deep-Stereo-Matching) repository.