anton-jeran / MESH2IR

This is the official implementation of our mesh-based neural network (MESH2IR) to generate acoustic impulse responses (IRs) for indoor 3D scenes represented using a mesh.

Home Page:https://anton-jeran.github.io/M2IR/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to generate the csv data inside **Paths** folder for a new given scene?

yyf17 opened this issue · comments

Very nice work and thank you very much for sharing.
Read.me has a sentence
``
For 3 different indoor scenes, we have stored sample source-recevier locations in a csv format inside Paths folder.
"
The question I want to ask is how is this data obtained?
How to generate the csv data inside Paths folder for a new given scene?
Are there any tools or scripts to share?
Thank you.

Hi,

Thank you for your interest in our project. We don't have a code to generate csv file for new environment.

Neural Sound rendering part of our project is done by our co-author Zhenyu Tang (https://royjames.github.io/zhy/). He rendered the video and gave me coordinates in a CSV file. I wrote embed_generator.py to create embeddings using the coordinates. The embedding can be created by appending a list like this.
embeddings = [mesh_path,folder_name,wave_name,source_list[s],listener_list[l]]
here
mesh_path --> graph location
folder_name,wave_name --> folder location and wav file name to save the output.
source_list[s] --> Source location
listener_list[l] --> Listener location

If you need to get more information on the coordinate system (where origin is located) and writing csv file, you need to contact Zhenyu (https://royjames.github.io/zhy/). You also can find details about the dataset here (https://arxiv.org/pdf/2204.01787.pdf).

Sorry, I could not help with regards to this problem.

@anton-jeran Thank you.