A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation

By Hamid Laga, Laurent Valentin Jospin, Farid Boussaïd, Mohammed Bennamoun. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

348 citations recorded by the source corpus.

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most widely used in the literature due to its strong connection to the human binocular system. Traditionally, stereo-based depth estimation has been addressed through matching hand-crafted features across multiple images. Despite the extensive amount of research, these traditional techniques still suffer in the presence of highly textured areas, large uniform regions, and occlusions. Motivated by their growing success in solving various 2D and 3D vision problems, deep learning for stereo-based depth estimation has attracted a growing interest from the community, with more than 150 papers published in this area between 2014 and 2019. This new generation of methods has demonstrated a significant leap in performance, enabling applications such as autonomous driving and augmented reality. In this paper, we provide a comprehensive survey of this new and continuously growing field of research, summarize the most commonly used pipelines, and discuss their benefits and limitations. In retrospect of what has been achieved so far, we also conjecture what the future may hold for deep learning-based stereo for depth estimation research.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a62615a1fb205ad506fc373dd4681bf21c730fc5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers (2020, background): “However, many of the best performing approaches are constrained to a manually pre-specified disparity range (typically a maximum of 192 px) [21].”
VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion (2023, background): “In general, stereo depth is more accurate than monocular depth since the former exploits epipolar geometry, but the latter relies on pattern recognition [73].”
Multi-View Mesh Reconstruction with Neural Deferred Shading (2022, neutral): “Traditionally, it has been approached by matching pixels between images, often based on photo-consistency constraints or learned features [16, 25].”
Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users (2020, methodology): “In addition, modern deep learning-based 3D object reconstruction [72] and disparity estimation in stereo vision [73] rely on self-supervised learning to overcome the time-consuming manual annotation of training data.”