shubhtuls / factored3d

Code release for "Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene"

Home Page:https://shubhtuls.github.io/factored3d/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene

Shubham Tulsiani, Saurabh Gupta, David Fouhey, Alexei A. Efros, Jitendra Malik.

Project Page

Note: Also see 3D-RelNet that improves on this work by incporporating relationships among objects. Teaser Image

Demo and Pre-trained Models

Please check out the interactive notebook which shows reconstructions using the learned models. To run this, you'll first need to follow the installation instructions to download trained models and some pre-requisites.

Training and Evaluating

To train or evaluate the (trained/downloaded) models, it is first required to download the SUNCG dataset and preprocess the data. Please see the detailed README files for Training or Evaluation of models for subsequent instructions.

Citation

If you use this code for your research, please consider citing:

@inProceedings{factored3dTulsiani17,
  title={Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene},
  author = {Shubham Tulsiani
  and Saurabh Gupta
  and David Fouhey
  and Alexei A. Efros
  and Jitendra Malik},
  booktitle={Computer Vision and Pattern Regognition (CVPR)},
  year={2018}
}

About

Code release for "Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene"

https://shubhtuls.github.io/factored3d/


Languages

Language:Python 67.9%Language:MATLAB 19.1%Language:C++ 13.0%Language:Objective-C 0.0%