PVRNet: Point-View Relation Neural Network for 3D Shape Recognition
Authors: Haoxuan You, Yifan Feng, Xibin Zhao, Changqing Zou, Rongrong Ji, Yue Gao9119-9126
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our proposed PVRNet has been evaluated on Model Net40 dataset for 3D shape classification and retrieval. Experimental results indicate our model can achieve significant performance improvement compared with the state-of-the-art models. |
| Researcher Affiliation | Academia | 1BNRist, KLISS, School of Software, Tsinghua University, China 2School of Information Science and Engineering, Xiamen University, China 3UMIACS, University of Maryland, College Park, United States |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | Our proposed PVRNet has been evaluated on Model Net40 dataset for 3D shape classification and retrieval. Princeton Model Net (Wu et al. 2015). Model Net contains 127,912 3D CAD models from 662 categories. Model Net40, a more commonly used subset containing 12,311 3D CAD models from 40 popular categories, is applied in our experiments. |
| Dataset Splits | Yes | Our training and test split setting follows (Wu et al. 2015). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using models like Alex Nets, MVCNN, and DGCNN but does not provide specific version numbers for software dependencies or libraries. |
| Experiment Setup | Yes | In our implementation, the 12 view features are extracted by 12 Alex Nets that share the same parameters like (Su et al. 2015). No view-pooling is performed to preserve the feature of each view. PVRNet is trained in an end-to-end fashion. The view feature extraction model and point cloud feature extraction model is initialized by the pre-trained MVCNN model and DGCNN model. And an alternative optimization strategy is adopted to update our framework. In first 10 epochs, the feature extraction model is fixed and we only fine-tune the other part (including relation score module, point-single-view fusion module and pointmulti-view fusion module). After the first 10 epochs, the all parameters are updated together to get better performance. |