Git Product home page Git Product logo

Comments (2)

JADGardner avatar JADGardner commented on June 1, 2024

Hi, thanks for your question and interest in NeuSky!

It should be version 0.3.4 but RENI++ does require some additional libraries that are not included in the nerfstudio docker base image, libopenexr-dev and openexr, which might be causing an issue. And nerfstudio may have been updated in such a way to cause an issue.

I've added a Dockerfile to this repo that should contain everything needed to install NeuSky and I've pushed a build of this to Dockerhub here. Inside this container you'll then just need to clone and install NeuSky using:

git clone https://github.com/JADGardner/neusky.git
cd neusky
python3.10 -m pip install -e .

You'll still need to download the RENI++ models using the script in the ns_reni repository (which I now notice I didn't have as an instruction in the README and will update this):

python3 ns_reni/scripts/download_models.py output/model/path/

And update this line in the config for NeuSky to point to this directory:

illumination_field_ckpt_path=Path("outputs/reni/reni_plus_plus_models/latent_dim_100/"),

Let me know if you have any other issues.

from neusky.

malfonsoarquimea avatar malfonsoarquimea commented on June 1, 2024

Hi! Thanks a lot!! I finally managed to create a working Docker image by building my own nerfstudio Docker image, based on a specific commit from the nerfstudio repo (commit 581ba95eabec3057b477824c87b7dba6fcc565f9) and adding neusky and reni++ on top of that. I believe the issue was that the version of nerfstudio used to develop Neusky's codebase falls somewhere between 0.3.4 and 1.0.0. Neusky is coded to work with the viewer in nerfstudio 0.3.4, but it also needs to be used with the RayGenerator implementation present in version 1.0.0, where the camera optimizer is not passed to the ray generator. Anyway, thanks a ton, I'll probably end up using your Docker image as the base for our project. Keep up the great work, you're a champ!

from neusky.

Related Issues (4)

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.