What is it about?
A comprehensive benchmark designed to evaluate and compare the performance of modern learning-based monocular depth estimation models.
Featured Image
Why is it important?
We introduce a modular and extensible benchmarking framework for monocular depth estimation, complete with an open-source codebase. The provided framework is convenient for adding new models, datasets, and metrics.
Perspectives
The provided codebase and approach can be reused for the development of benchmarks in other domains and tasks.
Vladimir Mashurov
ITMO University
Read the Original
This page is a summary of: MonoDeMB: Comprehensive Monocular DepthMap Benchmark, August 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3711896.3737394.
You can read the full text:
Resources
Contributors
The following have contributed to this page
