Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/chaene/hsp

Last synced: 3 months ago
JSON representation

Host: GitHub
URL: https://github.com/chaene/hsp
Owner: chaene
License: gpl-2.0
Created: 2018-02-16T18:12:45.000Z (over 6 years ago)
Default Branch: master
Last Pushed: 2018-05-23T18:08:55.000Z (over 6 years ago)
Last Synced: 2024-05-31T17:28:13.250Z (6 months ago)
Language: Lua
Size: 47.9 KB
Stars: 30
Watchers: 4
Forks: 7
Open Issues: 3
Metadata Files:
- Readme: README.md
- License: LICENSE.txt

Awesome Lists containing this project

README

        # Hierachical Surface Prediction

## Installation

Install [torch](http://torch.ch/)

Download [CImg](http://cimg.eu/) and place it in the torch-hsp subfolder. The file "CImg.h" needs to be in the path "torch-hsp/CImg/".

Install the torch package torch-hsp by running "luarocks make hsp-1.0-0.rockspec" in the torch-hsp folder

## Running Demo

A demo script is included which reconstructs a single image and outputs a mesh as obj file. It needs as input the pretrained network provided [here](https://drive.google.com/file/d/1it00XjWc7PnKAwVhPEtl2V96g3RPbi2V/view?usp=sharing).

th hspDemo.lua <GPU ID> <Trained Network File Name> <Input Image File Name>

## Training Network

Example parameter files are provided [here](https://drive.google.com/file/d/1it00XjWc7PnKAwVhPEtl2V96g3RPbi2V/view?usp=sharing).

The data is provided [here](https://drive.google.com/file/d/1xtJz5CEEPgYOtWP6Dr6nUWbUXPDMswh0/view?usp=sharing).

To train a network the paths to the shapenet dataset and the output folder in the "parameters.lua" file need to be adjusted first.

th trainNetworkHierarchical.lua <GPU ID> <Parameter File Name>

## License and Citation

The code is released as GPLv2.

When using the provided data make sure to respect the shapenet [license](https://shapenet.org/terms).

Please cite our paper when using the code.


C. Häne, S. Tulsiani, J. Malik, Hierarchical Surface Prediction for 3D Object Reconstruction, Proc. Int. Conf. on 3D Vision (3DV), 2017