Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
Authors: Mutian Xu, Junhao Zhang, Zhipeng Zhou, Mingye Xu, Xiaojuan Qi, Yu Qiao3056-3064
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters. |
| Researcher Affiliation | Academia | 1Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China 2The University of Hong Kong 3University of Chinese Academy of Sciences, China |
| Pseudocode | No | The paper describes its methods in detail with mathematical formulations, but does not include structured pseudocode or algorithm blocks (e.g., a figure or section explicitly labeled 'Pseudocode' or 'Algorithm'). |
| Open Source Code | Yes | Code is released on https://github.com/mutianxu/GDANet. |
| Open Datasets | Yes | We firstly evaluate GDANet on Model Net40 (Wu et al. 2015)... Our model is also tested on Scan Object NN by (Uy et al. 2019)... We employ Shape Net Part (Yi et al. 2016)... |
| Dataset Splits | No | The paper mentions '9843 training models and 2468 test models' for ModelNet40, but does not explicitly state a validation set or provide details on how data was split for validation, or reference predefined validation splits with citations. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., 'Python 3.8, PyTorch 1.9, and CUDA 11.1') needed to replicate the experiment. |
| Experiment Setup | No | The paper describes some aspects of the experimental setup such as data augmentation, point input size, and dynamic adjacency matrix calculation, but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or explicit training schedules. |