Multi View Stereo on Internet Images

Overview

Evaluating MVS in a CPC Scenario

This repository contains the set of artficats used for the ENGN8601/8602 research project. The thesis emphasizes on the following aspects:

  • Evaluating and Analysing the performance of existing learning-based MVS networks on internet images or in a CPC scenario.
  • Proposing a novel mask estimation module and depth estimation (with depth alignment) framework to estimate depth values of foreground objects.
  • Fusing the depthmaps estimated by the proposed methodology to compute complete point clouds (including foreground objects)

Installation

Recommended: python 3.7.7, cudatoolkit 10.2.* and conda.

The python libraries required are provided in the requirements.txt file. You can install the environment and necessary modules as follows or use your own approach:

Create a new conda environment and activate it:

conda create -n mvs
conda activate mvs

Install requirements.txt and opencv & pytorch separately (make sure pip is installed):

pip install -r requirements.txt
pip install opencv-python
pip install torch==1.8.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html

Data

Download the validation dataset extracted from MegaDepth dataset here and extract the all the images from the dataset to ref_images folder as subdirectories (create ref_images if it doesn't exist).

Usage

All the results have been included in the downloaded dataset already for ease of access to the results. The directory structure is given and explained as follows. The image subdirectories include reference images, npy files containing camera information, entropies, depthmaps (monocular, estimated and ground truth) etc.

  • All the images inside the ref_images directory contain a grid_outputs subdirectory which contain the best masks estimated for the reference image. This subdirectory also contains the plots with the .npy files for visualization.
  • All the images inside the ref_images directory contain ply and ply_gt subdirectories, which contain the 3D world points and .ply files depicting the estimated point cloud of that scene reconstructed by the proposed method.
  • The final_fused_scenes folder contains the point cloud generated by fusing multiple depthmaps obtained from different views of the same scene.

NOTE: You do not need to run the following steps in a sequence since required intermediate results are already provided in the images (such as entropy maps etc.), you can run any step directly.

1. Mask Estimation

Open the terminal and run the following command:

python masking.py

The 10 best masks with lowest binary cross entropy loss and IoU for each reference image is computed and saved inside a grid_outputs subdirectory inside each image directory. You can view the mask visualizations which are saved as .png. The masks are also saved as .npy files.

2. Calculating Error Metrics

To calculate the EPE, 1px and 3px errors between the estimated depthmaps and ground truth depthmaps, run the following command:

python calc_errors.py

3. 3D Reconstruction - Individual Point Clouds

To reconstruct ground truth point clouds and the estimated point clouds with foreground objects for each individual reference image, run the following command:

python pfm2ply_aligned.py                   # Point Clouds from Estimated Depthmaps (with foreground)
python pfm2ply_aligned_gt.py                # Point Clouds from Ground Truth Depthmaps

The point clouds will be saved in the ply and ply_gt image subdirectories respectively as .ply files along with the vertices of these point clouds saved as vertices.npy. This also generates the aligned absolute depthmap and saves the visualization along with the monocular depthmap estimated via the monocular depth estimation network inside the image directories.

4. Generating Scene Point Clouds

Since step 3 comptues individual point clouds, the next task is to merge the vertices of each individual point cloud to generate the point cloud for an entire scene. Run the following command:

python merge2ply.py

You can specify the set of images to be used for reconstructing each scene by editing the merge2ply file. All the scene point clouds are saved in final_fused_scenes folder.

Visualizations of Outputs

1. Mask Estimation

masks

2. 3D Reconstruction of Invidiual Depthmaps

3dr

3. Merged Point Clouds

3dr scenes

Supporting Repositories

I would like to give credit to the following repositories for assisting me in computing intermediate results necessary for the thesis:

Thank you!

Owner
Namas Bhandari
Machine Learning/Deep Learning/AI Enthusiast
Namas Bhandari
Cross-platform .NET Core pre-commit hooks

dotnet-core-pre-commit Cross-platform .NET Core pre-commit hooks How to use Add this to your .pre-commit-config.yaml - repo: https://github.com/juan

Juan Odicio 5 Jul 20, 2021
Stopmagic gives you the power of creating amazing Stop Motion animations faster and easier than ever before.

Stopmagic gives you the power of creating amazing Stop Motion animations faster and easier than ever before. This project is maintained by Aldrin Mathew.

Aldrin's Art Factory 67 Dec 31, 2022
Bu repoda python ile CAN-Bus çalışmalarını nasıl gerçekleyeceğiniz anlatılmaktadır.

CAN-Bus-with-Python "CAN Bus 1980'li yıllarda Robert BOSCH tarafından geliştirilmiş bir iletişim protokoldür. Hızlı ve hata oranının çok düşük olması

Yunus Emre Coşkun 16 Aug 29, 2022
Visual Python and C++ nanosecond profiler, logger, tests enabler

Look into Palanteer and get an omniscient view of your program Palanteer is a set of lean and efficient tools to improve the quality of software, for

Damien Feneyrou 1.9k Dec 26, 2022
:art: Diagram as Code for prototyping cloud system architectures

Diagrams Diagram as Code. Diagrams lets you draw the cloud system architecture in Python code. It was born for prototyping a new system architecture d

MinJae Kwon 27.5k Jan 04, 2023
A tool to help the Poly copy-reading process! :D

PolyBot A tool to help the Poly copy-reading process! :D Let's face it-computers are better are repeatitive tasks. And, in spite of what one may want

1 Jan 10, 2022
SuperCollider library for Python

SuperCollider library for Python This project is a port of core features of SuperCollider's language to Python 3. It is intended to be the same librar

Lucas Samaruga 65 Dec 22, 2022
A normal phoneNumber tracker made with python.

A normal phoneNumber tracker made with python.

CLAYZANE 2 Dec 30, 2021
High-level bindings to the Valhalla framework.

Valhalla for Python This spin-off project simply offers improved Python bindings to the fantastic Valhalla project. Installation pip install valhalla

GIS • OPS 20 Dec 13, 2022
A Python script to convert your favorite TV series into an Anki deck.

Ankiniser A Python3.8 script to convert your favorite TV series into an Anki deck. How to install? Download the script with git or download it manualy

37 Nov 03, 2022
Automated Content Feed Curator

Gathers posts from content feeds, filters, formats, delivers to you.

Alper S. Soylu 2 Jan 22, 2022
Discord's own Dumbass made for shits n' Gigs!

FWB3 Discord's own Dumbass made for shits n' Gigs! Please note: This bot is made to be stupid and funny, If you want to get into bot development you'r

1 Dec 06, 2021
Just some mtk tool for exploitation, reading/writing flash and doing crazy stuff

Just some mtk tool for exploitation, reading/writing flash and doing crazy stuff. For linux, a patched kernel is needed (see Setup folder) (except for read/write flash). For windows, you need to inst

Bjoern Kerler 1.1k Dec 31, 2022
This is a repository containing the backend and the frontend of a simple pokédex.

Pokémon This is a repository containing the backend and the frontend of a simple pokédex. This is a work in progress project! Project Structure 🗂 pok

André Rato 1 Nov 28, 2021
Providing a working, flexible, easier and faster installer than the one officially provided by Arch Linux

Purpose The purpose is to bring more people to Arch Linux by providing a working, flexible, easier and faster installer than the one officially provid

André Luís 0 Nov 09, 2022
Python Cheat Sheet

Introduction Pysheeet was created with intention of collecting python code snippets for reducing coding hours and making life easier and faster. Any c

CHANG-NING TSAI 7.5k Dec 30, 2022
It's an .exe file that can notify your chia profit and warning message every time automatically.

chia-Notify-with-Line 警示程式 It's an .exe file that can notify your chia profit and warning message every time automatically. 這是我自行設計的小程式,有轉成.exe檔了,可以在沒

You,Yu 1 Oct 28, 2021
A submodule of rmcrkd/ODE-Uniqueness

Heston-ODE This repo contains the Heston-related code that accompanies the article One-sided maximal uniqueness for a class of spatially irregular ord

0 Jan 05, 2022
Odoo. Open Source Apps To Grow Your Business.

Odoo Odoo is a suite of web based open source business apps. The main Odoo Apps include an Open Source CRM, Website Builder, eCommerce, Warehouse Mana

Odoo 27.6k Jan 09, 2023
Python project setup, updater, and launcher

pyLaunch Python project setup, updater, and launcher Purpose: Increase project productivity and provide features easily. Once installed as a git submo

DAAV, LLC 1 Jan 07, 2022