MonoDeMB: Comprehensive Monocular DepthMap Benchmark

Аннотация

In this paper, we introduce a comprehensive benchmark for learning-based monocular depth estimation methods. In recent years, depthmap calculation methods have achieved impressive results. The process of comparing the performance of different models requires a lot of resources and time, which can be costly for many developers. The goal of our benchmark is to provide a comparison of how the top models perform on various datasets. We present a table with results based on our tests performed on several popular datasets and one dataset introduced in this paper. In addition, we provide a toolkit that allows each model selected for the benchmark to be tested on any suitable dataset.