CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion

Authors: Zhenjiang Du, Jiale Dou, Zhitao Liu , Jiwei Wei, Guan Wang, Ning Xie, Yang Yang

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that our method achieves state-of-the-art performance on point cloud completion.
Researcher Affiliation Academia 1University of Electronic Science and Technology of China, Chengdu, China 2 Yibin Park, University of Electronic Science and Technology of China, Yibin, China 3Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou, China
Pseudocode No The paper describes the model architecture and components in text and diagrams (Figure 2 and Figure 3), but does not provide pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement about releasing open-source code or a link to a code repository.
Open Datasets Yes The dataset we used in our experiments is Shape Net Vi PC (Zhang et al. 2021).
Dataset Splits No The paper states: 'for each category, we randomly take about 1/3 of the total training data for training. For the test dataset, we used all the test data.' It does not explicitly mention a validation split with specific percentages or counts.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as GPU or CPU models.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in their implementation.
Experiment Setup Yes We train the network with a batch size of 32. The initial learning rate is 1e-4 and decayed by 0.7 after 20 epochs. The optimization is set to stop after 150 epochs. The initial value of α is set to 1, which will change with the number of iterations. After iterating 50 epochs, we set it to 0.5. The method s hyper-parameters (η, λ, ξ) are set to: (0.1, 0.1, 0.01).