(* Equal contributions)
1 Hikvision Research Institute, Santa Clara, USA
2 University of California, Los Angeles (UCLA), USA
3 Beijing Institute of Technology
This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an “analysis by synthesis” scheme and can be interpreted as a mode seeking and mode shifting process. The model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC such as Langevin dynamics. The model can be used to train a 3D generator network via MCMC teaching. The conditional version of the 3D shape descriptor net can be used for 3D object recovery and 3D object super-resolution. Experiments demonstrate that the proposed model can generate realistic 3D shape patterns and can be useful for 3D shape analysis.
The paper can be downloaded here.
The tex file can be downloaded here.
The poster can be downloaded here.
The CVPR 2018 Oral presentation can be downloaded here.
The Python code using tensorflow can be downloaded here
If you wish to use our code, please cite the following paper:
ContentsExp 1 : Experiment on 3D object synthesis
We evaluate a 3D generator trained by a 3D DescriptorNet in cooperative training scheme on experiments of latent space interpolation and 3D object arithmetic.
Exp 4.1: Interpolation
Exp 4.2: 3D Object Arithmetic
The following shows 3D object arithmetic by the 3D generator net. It encodes semantic knowledge of 3D shapes in the latent space.
We first train a single model on all categories of the training set of ModelNet10 dataset in an unsupervised manner. Then we use the model as a feature extractor. We train a multinomial logistic regression classifier from labeled data based on the extracted feature vectors for classification. The following shows 3D object classification results on ModelNet10 dataset. We evaluate the classification accuracy on the testing data using the one-versus-all rule.
We thank Erik Nijkamp for his help on coding. We thank Siyuan Huang for helpful discussions.