Giter Site home page Giter Site logo

youtube3d's Introduction

Learning Single-Image Depth from Videos using Quality Assessment Networks

Code for reproducing the results in the following paper:

Learning Single-Image Depth from Videos using Quality Assessment Networks
Weifeng Chen, Shengyi Qian, Jia Deng
Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

Please check the project site for more details.

Example outputs on the Depth in the Wild (DIW) test set

qual_outputs

Setup

  1. The code is written in python 2.7.13, using pytorch 0.2.0_4. Please make sure that you install the correct pytorch version as later versions may cause the code to break.

  2. Clone this repo.

git clone [email protected]:princeton-vl/YouTube3D.git
  1. Download data_model.tar.gz into path YouTube3D, then untar:
cd YouTube3D
tar -xzvf data_model.tar.gz
  1. Download and unpack the images from Depth in the Wild dataset. Edit DIW_test.csv under YouTube3D/data so that all the image paths are absolute paths.

Evaluating the pretrained models

To evaluate the pre-trained model EncDecResNet trained on ImageNet + ReDWeb + DIW + YouTube3D on the DIW dataset, run the following command:

cd YouTube3D/src 
python test.py -t DIW_test.csv -model exp/YTmixReD_dadlr1e-4_DIW_ReDWebNet_1e-6_bs4/models/model_iter_753000.bin

In case you want to get the qualitative outputs, append a -vis flag and the qualitative outputs will be in the folder visualize:

mkdir visualize
python test.py -t DIW_test.csv -model exp/YTmixReD_dadlr1e-4_DIW_ReDWebNet_1e-6_bs4/models/model_iter_753000.bin -vis

To evaluate the pre-trained model HourglassNetwork trained on NYU + DIW + YouTube3D on the DIW dataset, run the following command:

python test.py -t DIW_test.csv -model exp/Hourglass/models/best_model_iter_852000.bin

Contact

Please send any questions or comments to Weifeng Chen at [email protected].

youtube3d's People

Contributors

wfchen-umich 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

youtube3d's Issues

Pytorch Version

Can you please let me know whether we can compile the code with Pytorch version>=1.0 ?

Because to compile with Pytorch 0.2 it requires Cuda7.5 and Cuda7.5 is only compatible upto ubuntu 14.04 version.

HourglassNet Checkpoint

Hi, Will it be possible to provide hourglassnet model python file along with model checkpoint for which you reported the analysis in the first column and Table 3. in the paper here
https://arxiv.org/pdf/1806.09573.pdf

I want to use the checkpoint model to initialize hourglass model and finetune it for another task that involves depth estimation in different settings.

Thanks
Aman Raj

SfM component ?

I can not find code of SfM component , will you release it later ?

Training on the YT3D and DIW dataset.

I have tried to use the yt3d dataset to train a hourglass network. However, I didn’t find any decrease of the WKDR value. It is about 30% all the time. While WKDR value can decrease obviously when training on the DIW dataset. What is the problem? I used Adam solver with a learning rate of 1e-4. b_sort=True, b_oppi=False, bs=4. Thanks.

Hourglass - NYU + DIW model?

First - great work on the paper!

I was wondering if you still had the baseline hourglass model you compare to in Table3 of the paper, first row - Hourglass network pretrained using DIW and NYU? I know I could be asking on the original DIW repo, but a pytorch version would be ideal if at all possible.

I'm planning to use it as a baseline for an upcoming piece of work.
Thanks a lot

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.