MAT-Net: Medial Axis Transform Network for 3D Object Recognition
Authors: Jianwei Hu, Bin Wang, Lihui Qian, Yiling Pan, Xiaohu Guo, Lingjie Liu, Wenping Wang
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results illustrate that MAT-Net demonstrates competitive or better performance on 3D shape recognition than state-of-the-art methods, and prove that MAT representation has excellent capacity in 3D deep learning, even in the case of low resolution. |
| Researcher Affiliation | Academia | 1School of Software, Tsinghua University, China 2Beijing National Research Center for Information Science and Technology (BNRist), China 3Department of Computer Science, The University of Texas at Dallas, United States of America 4Department of Computer Science, The University of Hong Kong, Hong Kong |
| Pseudocode | No | The paper does not contain explicit pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper states that an open MAT dataset was constructed, but it does not provide explicit access to the source code for the MAT-Net methodology itself. |
| Open Datasets | Yes | We constructed an open MAT data set called Model Net40MAT for research community. SHREC15: The database has 1200 watertight meshes which are equally classified into 50 categories. |
| Dataset Splits | Yes | We use 8, 208 objects for training and 2, 035 objects for testing. We use five fold cross validation to acquire classification accuracy. |
| Hardware Specification | Yes | Our network is implemented with Tensor Flow on an NVIDIA TITAN Xp. |
| Software Dependencies | No | The paper mentions 'Tensor Flow' but does not specify a version number or other software dependencies with version numbers. |
| Experiment Setup | Yes | All experiments are trained with a large-enough number of neighbors K = 16. We jitter the initial medial spheres (with random translation of Gaussian distribution N(0, 0.008) and clipped to 0.01 to generate the augmented spheres. Edge-Net has only 1 convolution layer with output channel of 32. The first CONV module of Feature Capture Module has two convolution layers and the second has three convolution layers. Their filters size are {64,64,128,256,1024}. The convolution kernel size of the first layer is 1 4, and the rest are 1 1. FC module has two fully connected layers and filters size are {512,256}. The loss function includes cross entropy loss for classification and L2 loss of feature transformation matrix. The batch size of Model Net40-MAT classification is 32, and 16 for SHREC15. |