Code Monkey home page Code Monkey logo

orion's Introduction

ORION

Here you can find the code for the BMVC 2017 version of "Orientation-boosted Voxel Nets for 3D Object Recognition", a.k.a ORION.

teaser

If you use this code for research please cite:

@InProceedings{SZB17a,
  author       = "N. Sedaghat and M. Zolfaghari and E. Amiri and T. Brox",
  title        = "Orientation-boosted voxel nets for 3D object recognition",
  booktitle    = "British Machine Vision Conference (BMVC)",
  month        = " ",
  year         = "2017",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2017/SZB17a"
}

Caffe Installation

Please download, build and install the version of caffe introduced here -- we use it for the provided 3D augmentation capabilities.

Modelnet40 Aligned Objects

Modelnet40 aligned objects can be downloaded from the links below. If you use this modified dataset, please also cite the following work from which we borrowed techniques for the auto-alignment:

@InProceedings{SB15,
  author       = "N. Sedaghat and T. Brox",
  title        = "Unsupervised Generation of a Viewpoint Annotated Car Dataset from Videos",
  booktitle    = "IEEE International Conference on Computer Vision (ICCV)",
  year         = "2015",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2015/SB15"
  }

Manually-aligned Modelnet40

Auto-aligned Modelnet40

Auto-alignment code will be published soon.

orion's People

Contributors

nimsed 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  avatar  avatar  avatar  avatar  avatar

orion's Issues

Questions about Manually-aligned Modelnet40

Hi, thanks for your work. I have some questions about the Manually-aligned Modelnet40 you provided.

  1. Is the data in .off file the aligned object? or it is the same thing as official modelnet40 data and we need to rotate the objects using the .annot file?
  2. Can you provide more information about how to use the .annot file? There are two lines in the .annot file. The first line is the rotation angle around z aixs, isn't it? what does the second line mean? It seems the second line is always 0?
    Thank you!

Opening tar file results in one big file

If I open the tar file on WIndows using 7zip or winrar, I find inside one big file. The problem is that the .tar file should renamed to .tar.gz if you want 7zip or winrar to correctly identify the file contents: then all the files and folders appear.

Is the auto-alignment code available?

Hi, may I know if the auto-alignment code was published? It was mentioned that the code will be published soon, but I could not find a link.

Thanks!

How to read the alligned dataset?

Hello,

The provided alligned dataset does not include an extension or any information about parsin it. I use python.

I tried to read it as a binary file with numpy and I received an array with shape (1249415680,).

I know it is an old project hope you are still monitoring it. Thanks for sharing this awesome work guys.

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.