Pixel2Mesh

This repository contains the TensorFlow implementation for the following paper

Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (ECCV2018)

Nanyang Wang, Yinda Zhang, Zhuwen Li, Yanwei Fu, Wei Liu, Yu-Gang Jiang.

---

Note: This is a fork of nywang16/Pixel2Mesh with work-in-progress changes. See Fork status below, and CLAUDE.md for an architecture overview and current caveats.

Fork status

This fork is migrating the original Python 2.7 + TensorFlow 1.x code toward Python 3 / TensorFlow 2 (via tensorflow.compat.v1). The migration is in progress, so the tree is currently in a mixed state:

• The entry scripts (train.py, eval_testset.py, demo.py) now import tensorflow.compat.v1; the modules under p2m/ have not all been ported yet.
• demo.py has been adapted to batch-process a directory of images rather than the single --image flow described below.
• Known gaps: eval_testset.py references p2m.cd_dist while the working module is p2m/chamfer.py; some modules still use Python-2-only constructs (cPickle, Queue, print statements).

Refer to CLAUDE.md for the full architecture and the up-to-date list of caveats. Everything below this section is the original upstream README.

---

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 demo developed by Mathias Gatti using Google Colab.

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+)
• TFLearn

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

Installation

If you use CD and EMD for training or evaluation, we have included the cuda implementations of Fan et. al. 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 dataset for 3D models, and rendered views from 3D-R2N2:
When using the provided data make sure to respect the shapenet license.

Below is the complete set of training data. Download it into the Data/ folder.

https://drive.google.com/open?id=131dH36qXCabym1JjSmEpSQZg4dmZVQid

The training/testing split can be found in Data/train_list.txt and Data/test_list.txt

Each .dat file in the provided data contain:

• 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.

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.
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