# Pixel2Mesh
This repository contains the TensorFlow implementation for the following paper</br>
[Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (ECCV2018)](http://openaccess.thecvf.com/content_ECCV_2018/papers/Nanyang_Wang_Pixel2Mesh_Generating_3D_ECCV_2018_paper.pdf)</br>
Nanyang Wang, [Yinda Zhang](http://robots.princeton.edu/people/yindaz/), [Zhuwen Li](http://www.lizhuwen.com/), [Yanwei Fu](http://yanweifu.github.io/), [Wei Liu](http://www.ee.columbia.edu/~wliu/), [Yu-Gang Jiang](http://www.yugangjiang.info/).
#### Citation
If you use this code for your research, please consider citing:
@inProceedings{wang2018pixel2mesh,
title={Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images},
author={Nanyang Wang and Yinda Zhang and Zhuwen Li and Yanwei Fu and Wei Liu and Yu-Gang Jiang},
booktitle={ECCV},
year={2018}
}
# Try it on Colab
Installing all the dependencies might be tricky and you need a computer with a CUDA enabled GPU. To get started fast you can just try [this](https://colab.research.google.com/drive/13xkSkvPaF5GU6Wpf35nVHUdP77oBVHlT#scrollTo=xXxbMrF4fdZs) demo developed by [Mathias Gatti](https://github.com/mathigatti) using Google Colab.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/13xkSkvPaF5GU6Wpf35nVHUdP77oBVHlT#scrollTo=xXxbMrF4fdZs)
# Project Page
The project page is available at https://nywang16.github.io/p2m/index.html
# Dependencies
Requirements:
* Python2.7+ with Numpy and scikit-image
* [Tensorflow (version 1.0+)](https://www.tensorflow.org/install/)
* [TFLearn](http://tflearn.org/installation/)
Our code has been tested with Python 2.7, **TensorFlow 1.3.0**, TFLearn 0.3.2, CUDA 8.0 on Ubuntu 14.04.
# News
- Nov. 8, we update the script for generate auxiliary data.
# Running the demo
```
git clone https://github.com/nywang16/Pixel2Mesh.git
cd Data/
```
Download the pre-trained model and unzip to the `Data/` folder.
* https://drive.google.com/file/d/1gD-dk-XrAa5mfrgdZSunjaS6pUUWsZgU/view?usp=sharing
```
unzip checkpoint.zip
```
#### Reconstructing shapes
python demo.py --image Data/examples/plane.png
Run the demo code and the output mesh file is saved in `Data/examples/plane.obj`
#### Input image, output mesh
<img src="./Docs/images/plane.png" width = "330px" /><img src="./Docs/images/plane.gif" />
# Installation
If you use CD and EMD for training or evaluation, we have included the cuda implementations of [Fan et. al.](https://github.com/fanhqme/PointSetGeneration) in external/
cd Pixel2Mesh/external/
Modify the first 3 lines of the makefile to point to your nvcc, cudalib and tensorflow library.
make
# Dataset
We used the [ShapeNet](https://www.shapenet.org) dataset for 3D models, and rendered views from [3D-R2N2](https://github.com/chrischoy/3D-R2N2):</br>
When using the provided data make sure to respect the shapenet [license](https://shapenet.org/terms).
Below is the complete set of training data. Download it into the `Data/` folder.
https://drive.google.com/open?id=131dH36qXCabym1JjSmEpSQZg4dmZVQid </br>
The training/testing split can be found in `Data/train_list.txt` and `Data/test_list.txt` </br>
Each .dat file in the provided data contain: </br>
* The sampled point cloud (with vertex normal) from ShapeNet. We transformed it to corresponding coordinates in camera coordinate based on camera parameters from the Rendering Dataset.
**Input image, ground truth point cloud.**</br>
<img src="./Docs/images/car_example.png" width = "350px" />
![label](./Docs/images/car_example.gif)
# Training
python train.py
You can change the training data, learning rate and other parameters by editing `train.py`
The total number of training epoch is 30; the learning rate is initialized as 3e-5 and drops to 1e-5 after 25 epochs.
# Evaluation
The evaluation code was released, please refer to `eval_testset.py` for more details.
Notice that the 3D shape are downscaled by a factor of 0.57 to generate rendering. As result, all the numbers shown in experiments used 0.57xRaw Shape for evaluation. This scale may be related to the render proccess, we used the rendering data from 3DR2N2 paper, and this scale was there since then for reason that we don't know.
# Statement
This software is for research purpose only. </br>
Please contact us for the licence of commercial purposes. All rights are preserved.
# Contact
Nanyang Wang (nywang16 AT fudan.edu.cn)
Yinda Zhang (yindaz AT cs.princeton.edu)
Zhuwen Li (lzhuwen AT gmail.com)
Yanwei Fu (yanweifu AT fudan.edu.cn)
Yu-Gang Jiang (ygj AT fudan.edu.cn)
# License
Apache License version 2.0
没有合适的资源?快使用搜索试试~ 我知道了~
Pixel2Mesh:从单个RGB图像生成3D网格模型。在ECCV2018中_Python_下载.zip
共86个文件
png:35个
py:17个
obj:7个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 27 浏览量
2023-04-30
23:38:10
上传
评论
收藏 5.58MB ZIP 举报
温馨提示
Pixel2Mesh:从单个RGB图像生成3D网格模型。在ECCV2018中_Python_下载.zip
资源推荐
资源详情
资源评论
收起资源包目录
Pixel2Mesh:从单个RGB图像生成3D网格模型。在ECCV2018中_Python_下载.zip (86个子文件)
Pixel2Mesh-master
.gitattributes 44B
GenerateData
1a0bc9ab92c915167ae33d942430658c
model.obj 5.31MB
rendering
09.png 5KB
19.png 8KB
05.png 6KB
02.png 8KB
10.png 8KB
08.png 7KB
00.png 6KB
04.png 7KB
12.png 7KB
15.png 5KB
01.png 6KB
03.png 7KB
23.png 5KB
11.png 5KB
13.png 4KB
07.png 7KB
renderings.txt 168B
21.png 6KB
17.png 8KB
16.png 6KB
rendering_metadata.txt 1KB
20.png 6KB
18.png 6KB
14.png 5KB
06.png 4KB
22.png 8KB
model_normal.xyz 1.11MB
model.xyz 220KB
model.mtl 3KB
1_sample_points.txt 169B
3_camera_transform.py 2KB
upsample.mlx 542B
generate_data.py 3KB
init_obj
init3.png 132KB
init1.png 40KB
init3.obj 225KB
init2.png 71KB
init1.obj 7KB
init2.obj 53KB
4_make_auxiliary_dat_file.ipynb 16KB
2_generate_normal.py 3KB
LICENSE 17KB
eval_testset.py 6KB
Docs
images
car_example.png 13KB
plane.gif 146KB
plane.png 5KB
car_example.gif 949KB
external
makefile 1KB
tf_nndistance_g.cu.o 25KB
approxmatch.cu 5KB
tf_nndistance_so.so 67KB
tf_approxmatch.py 4KB
tf_nndistance.cpp 13KB
tf_nndistance.py 3KB
approxmatch.cpp 7KB
tf_nndistance_g.cu 4KB
tf_approxmatch_g.cu 9KB
tf_approxmatch.cpp 14KB
tf_approxmatch_g.cu.o 33KB
tf_approxmatch_so.so 84KB
train.py 4KB
demo.py 4KB
README.md 5KB
p2m
utils.py 2KB
__init__.py 0B
inits.py 2KB
losses.py 3KB
chamfer.py 4KB
fetcher.py 2KB
layers.py 9KB
models.py 11KB
api.py 10KB
Data
test_list.txt 3.17MB
train_list.txt 12.67MB
examples
car.png 8KB
chair.png 5KB
gun.png 4KB
table.png 5KB
lamp.png 5KB
plane.png 4KB
ellipsoid
info_ellipsoid.dat 906KB
face3.obj 75KB
face2.obj 16KB
face1.obj 4KB
共 86 条
- 1
资源评论
快撑死的鱼
- 粉丝: 1w+
- 资源: 9156
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功