Repository files navigation

This repository contains a tensorflow implementation for the paper "Learning Descriptor Networks for 3D Shape Synthesis and Analysis". (http://www.stat.ucla.edu/~jxie/3DDescriptorNet/3DDescriptorNet.html)

• Python 2.7 or Python 3.3+
• Tensorflow r1.3+
• Install required Python libraries

  pip install numpy scipy

• Clone this repo:

  git clone https://github.com/jianwen-xie/3DDescriptorNet.gitcd 3DDescriptorNet

• Downloadvolumetric data and save it to./data directory.The dataset contains 10 categories of voxelizations ofModelNet10.

• Downloadpretrained models and save it to the cloned directory.

• Train the synthesis model onnight stand category:

  python train.py --category night_stand --data_dir ./data/volumetric_data/ModelNet10 --output_dir ./output

• Visualize the generated results using theMATLAB code invisualization/visualize.m, e.g.

  addpath('visualization')visualize('./output/night_stand/synthesis','sample2990.mat')

• Evaluate synthesized results using the evaluation code in./evaluation

• You can download oursynthesized results and test on it.

• Train the recovery model onsofa category:

  python rec_exp.py --category sofa \                  --num_epochs 1000 \                  --batch_size 50 \                  --step_size 0.07 \                  --sample_steps 90

• Test the recovery model:

  1. Download theincomplete data and save it to./data directory. For each category involumetric_data, theincomplete data contains: 1)incomplete_test.mat: 70% randomly corrupted testing data 2)masks.mat: The mask to corrupt the testing data. 3.original_test.mat: original testing data for comparison.
  2. You can download ourpretrained model to test recovery.
  3. Run recovery on the corrupted data

  python rec_exp.py --test --category sofa \                  --ckpt pretrained_model/recovery/sofa/sofa.ckpt \                  --incomp_data_path ./data/incomplete_data \                  --batch_size 50 \                  --step_size 0.07 \                  --sample_steps 90

• Train the super resolution model ontoilet category:

  python sr_exp.py --category toilet \                  --cube_len 64 \                  --scale 4 \                  --num_epochs 500 \                  --batch_size 50 \                  --step_size 0.01 \                  --sample_steps 10

• Test the super resolution model:

  python rec_exp.py --test --category toilet \                  --ckpt ./output/toilet/checkpoints/model.ckpt-490 \                  --cube_len 64 \                  --scale 4 \                  --batch_size 50 \                  --step_size 0.01 \                  --sample_steps 10

• Train Classification using Logistic Regression (pretrained model):

  python train_classification.py --classifier_type logistic --ckpt pretrained_models/classification/model.ckpt

• Train Classification using SVM:

  python train_classification.py --classifier_type svm --ckpt pretrained_models/classification/model.ckpt

@inproceedings{3DDesNet,    title={Learning Descriptor Networks for 3D Shape Synthesis and Analysis},    author={Xie, Jianwen and Zheng, Zilong and Gao, Ruiqi and Wang, Wenguan and Zhu Song-Chun and Wu, Ying Nian},    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},    year={2018}}

For any questions, please contact Jianwen Xie (jianwen@ucla.edu) and Zilong Zheng (zilongzheng0318@ucla.edu).