This repository is an extension of original PyTorch implementation of "MVDepthNet: real-time multiview depth estimation neural network" (https://github.com/HKUST-Aerial-Robotics/MVDepthNet)

• The MVDepthNet repository by Wang et. al. generate depth for two images. I have extended it for multiple images.

--- Prerequisites: PyTorch: The PyTorch version used in the implementation is 0.3, OpenCV, NumPy

--- Run: python3 MV_DepthNet.py

--- PS:

1. Download the model paramters from https://github.com/HKUST-Aerial-Robotics/MVDepthNet
2. I have used images and camera parameters from https://vision.in.tum.de/data/datasets/rgbd-dataset/file_formats