A survey on deep learning techniques for stereo-based depth estimation about digital_image_processing HOT 2 OPEN

from digital_image_processing.

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 of a new generation of methods that has demonstrated a significant leap in performance, enabling applications such as autonomous driving andaugmented reality. In this article, 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.

from digital_image_processing.