Giter Club home page Giter Club logo

nerf_unity's Introduction

nerf_Unity

๐Ÿ’Ž Project page (live demo!)

Unity projects for my implementation of nerf_pl (Neural Radiance Fields)

Update : Now you can view the volume from inside! See video

Tutorial and demo videos

Installation and usage

This project is built on Unity 2019.3.9f1 on Windows. It contains 3 scenes (under Scenes/ folder):

Due to large size of the files, I put the assets in release, you need to download from there and import to Unity. Make sure you download them and put under Assets/ before opening Unity. Follow the instructions below for each scene:

If you want to use your own data, please see this and videos to train on your own data first.

MeshRender

Render reconstructed meshes. image

Data preparation

  1. Download the mesh files (*.ply) from here
  2. Follow the below image to add the mesh to scene:
    • Select gameobject
    • Drag mesh into the missing parts image

MixedReality

Render a real scene with correct depth values, where you can add virtual objects and get accurate occlusion effect (visual effect only). image

Data preparation

If you're using linux, it seems StreamingAssets cannot be correctly imported #2. In this case, try to manually enter the path to files into the missing parts.

VolumeRender

Volume render a virtual object.

image

Data preparation

  1. Download the volume files (*.vol) from here
  2. Follow the below image to add the volume to scene:
    • Select gameobject
    • Drag vol into the missing part image

nerf_unity's People

Contributors

kwea123 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

nerf_unity's Issues

A few tricky parts about set up

  1. If Unity is opened before you've downloaded the separate assets it deletes the .meta files and you therefore lose any import settings for those files. Maybe tell people to download them before they open Unity
  2. Make it clear that the assets have to be placed in the root of Assets. Anywhere else and they won't link to the correct .meta files.

Mixed Reality demo volumes missing

Hi, great work on the project!
I can't seem to find the T-Rex and Triceratops vols either in the repo or the release downloads, so can't get the Mixed reality demo to work.

Are these files included anywhere?

Also, I was wondering if there are any instructions to export volumes from NeRFs made using your NeRF repo?

Thanks

issues with generating poses for own dataset

Hi!

I am a student Artificial Intelligence and I am working on a project using NeRF with a group of other students. We are in possession of a dataset that is made by a company we do the project for. The data consists of images such as the one that is attached (but the whole object is visible, right now it is copressed).

Webp net-compress-image

We are working with your notebooks and we find them highly useful! Thank you for this contribution.

However, we cannot generate poses. The output of the LLFF script is:

Features extracted
Features matched
Sparse map created
Finished running COLMAP, see /content/drive/My Drive/nerf/kan_new/colmap_output.txt for logs
Post-colmap
Traceback (most recent call last):
  File "imgs2poses.py", line 18, in <module>
    gen_poses(args.scenedir, args.match_type)
  File "/content/LLFF/llff/poses/pose_utils.py", line 274, in gen_poses
    poses, pts3d, perm = load_colmap_data(basedir)
  File "/content/LLFF/llff/poses/pose_utils.py", line 14, in load_colmap_data
    camdata = read_model.read_cameras_binary(camerasfile)
  File "/content/LLFF/llff/poses/colmap_read_model.py", line 115, in read_cameras_binary
    with open(path_to_model_file, "rb") as fid:
FileNotFoundError: [Errno 2] No such file or directory: '/content/drive/My Drive/nerf/kan_new/sparse/0/cameras.bin'

And sometimes we do not have this error but it only says 'no poses could be extracted'.

Here also the output of colmap:
colmap_output(1).txt

Do you know what could've caused this? What can we do better? We really hope to hear from you!

How to generate own volumes

Hi Kwea. How can I convert my own NeRF scenes into the requested volume format? i.e. how to convert .npy to .vol

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.