Midas

Monocular Depth Estimation with Unity Sentis using MiDaS[^1] models

Asset Store

OpenUPM · Documentation · Forum · Hugging Face

This project is dual-licensed. You can either get it here on GitHub under the MIT License, or — if you find it useful and want to support the development — for a small price on the Unity Asset Store.

Usage

Please refer to the Documentation for usage guides.

References

[^1]: René Ranftl and Katrin Lasinger and David Hafner and Konrad Schindler and Vladlen Koltun. Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 3, 2022