https://github.com/hjimce/Depth-Map-Prediction

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
https://github.com/hjimce/Depth-Map-Prediction

Last synced: about 2 months ago
JSON representation

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

• Host: GitHub
• URL: https://github.com/hjimce/Depth-Map-Prediction
• Owner: hjimce
• License: gpl-3.0
• Created: 2015-11-23T09:08:00.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2015-11-24T10:31:56.000Z (almost 9 years ago)
• Last Synced: 2024-04-11T07:46:26.031Z (5 months ago)
• Language: Python
• Size: 4.51 MB
• Stars: 182
• Watchers: 6
• Forks: 58
• Open Issues: 4
• Metadata Files:
  • Readme: README
  • License: LICENSE

Awesome Lists containing this project

• awesome-starred - hjimce/Depth-Map-Prediction - Depth Map Prediction from a Single Image using a Multi-Scale Deep Network (others)

README

        
=========================================================================

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

=========================================================================

Authors: David Eigen, Christian Puhrsch and Rob Fergus

Email:   [email protected], [email protected], [email protected]

Requirements

-------------

* theano

* numpy, scipy

* PIL or Pillow

Running the Demo

-----------------

The demo loads the depth prediction network, compiles a theano function for

inference, and infers depth for a single image.  To run:

> THEANO_FLAGS=device=gpu0 python demo_depth.py

This should create a file called "demo_nyud_depth_prediction.png" with the

predicted depth for the input "demo_nyud_rgb.jpg".  (Substitute the gpu you

want to run on for gpu0).

Other Information

------------------

This tree contains code for depth prediction network inference.  While there is

some code relating to training, much of the training code including most data

processing is not provided here.  We may release this in the future, however.

While developing this project, we made a few modifications in theano not

currently part of the main codeline.  While the above instructions should work

for inference on a current unmodified theano build, it may take up more GPU

memory than needed due to use of test values for shape information.  The git

patch file "theano_test_value_size.patch" is also included and might be used to

enable this feature on your own tree.