Code Monkey home page Code Monkey logo

matchnerf's People

Contributors

donydchen avatar haofeixu avatar lyndonzheng avatar qianyiwu 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

Forkers

whuhxb alexandor91 paperwave ayankumarbhunia alakia

matchnerf's Issues

dtu and intrinsics

hello, why the intrinsics need *4?, and how the w/2 and h/2 are not the half of the pixel of images? thank you

render with more than 3 view

Hi, I try your demo and the result is really great. It seems that the matchnerf_3v_ibr.pth can only render scene with 3 views. What should I do to render a scene with more than 3 views such as orchid in LLFF dataset(25 views)? Also, I wanna know how to adjust the render poses. Thanks in advance!

Evaluation with 2 views as input

Thanks for your excellent open-source work. I want to evaluate the performance of your method with two views as input, I run the following command:

python test.py --yaml=test --name=matchnerf_3v --n_src_views=2

but there was an error, as follows:

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for CondNeRF:
size mismatch for pts_bias.weight: copying a param with shape torch.Size([128, 22]) from checkpoint, the shape in current model is 
torch.Size([128, 18]).

Is this because the model changes when the number of input views changes? If so, is it convenient for you to provide a pre-trained model with 2 view inputs？Thank you!

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.