Git Product home page Git Product logo

360opticalflow-tangentimages's People

Contributors

yuanmingze avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

360opticalflow-tangentimages's Issues

Unable to reproduce the accuracy of the paper

Hi! Thanks for your wonderful work.

I'm having problems with precision that cannot be reproduced. When I run the data demo in this repository directly, I get epe=7.89:
image

However, when I downloaded the entire Replica360 dataset and tested it, for example, the line split, I got the following results:
image
in which epe=27.39, and it‘s significantly higher than the 5.84 error reported in the paper.

I didn't make any changes to your code or parameters. During testing, I additionally used a valid mask to filter out unreliable pixels, including Replica's own valid mask, excessive optical flow and optical flow with a true value of nan, which is consistent with the selection of valid pixels in the repo:
image

How do I reproduce the accuracy in the paper? Are there any thresholds that need to be adjusted?

Looking forward to your guidance! =)

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.