Midas : A Machine Learning Model for Depth Estimation

Original Source Here
Overview
Midas is a machine learning model that estimates depth from an arbitrary input image.
Architecture
Various datasets containing depth information are not compatible in terms of scale and bias. This is due to the diversity of measuring tools, including stereo cameras, laser scanners, and light sensors. Midas introduces a new loss function that absorbs these diversities, thereby eliminating compatibility issues and allowing multiple data sets to be used for training simultaneously.
Midas uses multiple datasets for training, as shown in the table below. Therefore, it can estimate the depth of images in various conditions and environments.
In addition, 3D movies were also used for training to complement the existing data set.
Below is the loss function introduced by Midas.
The architecture of the network is based on ResNet.
Usage
You can use the following command to run Midas on the webcam video stream in ailia SDK.
$ python3 midas.py -v 0
You can also choose the higher precision v2.1 or the faster v2.1 small model, which runs five times faster than the regular model and enables real-time processing.
$ python3 midas.py -v 0 -v21
$ python3 midas.py -v 0 -v21 -t small
Here are some results.
AI/ML
Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot
via WordPress https://ramseyelbasheer.io/2021/05/27/midas-a-machine-learning-model-for-depth-estimation/