Monocular Depth Estimation Using State-of-the-art Algorithms: A Review

Keywords:
Depth Estimation, Monocular Depth Estimation, Computer Vision, Deep Learning, Comparison

Abstract:
Monocular Depth Estimation is the process of calculating the depth value of each pixel given a single RGB image. This challenging computer vision task is the main prerequisite for determining scene understanding for applications such as 3D scene reconstruction, augmented and virtual reality. Additionally, a lot of robotics issues, like mapping, localization, and obstacle avoidance for terrestrial and aerial vehicles, depend on depth information. Five monocular depth estimation techniques are compared. This comparison focuses on how generalizable the methods are. According to this study, monocular depth estimation techniques frequently exhibit artifacts when used on images that are not part of the training set, despite performing well on images that are similar to the training images. We test the various approaches using photos that resemble training data as well as paintings or images with odd perspectives.

CITATION:

IEEE format

Copy to clipboard

T. Dogandžić, A. Jovanović, “Monocular Depth Estimation Using State-of-the-art Algorithms: A Review,” in Sinteza 2023 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2023, pp. 100-104. doi:10.15308/Sinteza-2023-100-104

APA format

Copy to clipboard

Dogandžić, T., Jovanović, A. (2023). Monocular Depth Estimation Using State-of-the-art Algorithms: A Review. Paper presented at Sinteza 2023 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2023-100-104

BibTeX format
Download

RefWorks Tagged format
Download