MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment

Authors: Zicheng Zhang, Wei Sun, Xiongkuo Min, Qiyuan Wang, Jun He, Quan Zhou, Guangtao Zhai

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that our approach outperforms all compared state-of-the-art methods and is far ahead of previous no-reference PCQA methods, which highlights the effectiveness of the proposed method. Extensive experiments show that MM-PCQA achieves the best performance among the compared state-of-the-art methods (even including the FR-PCQA methods).
Researcher Affiliation Collaboration Zicheng Zhang1 , Wei Sun1 , Xiongkuo Min1 , Qiyuan Wang3 , Jun He3 , Quan Zhou3 and Guangtao Zhai1,2 1Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University 2Mo E Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University 3Bilibili Inc, Shanghai, China
Pseudocode No The paper describes the method using prose and mathematical equations but does not include any pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/zzc-1998/MM-PCQA.
Open Datasets Yes To test the performance of the proposed method, we employ the subjective point cloud assessment database (SJTUPCQA) [Yang et al., 2020a], the Waterloo point cloud assessment database (WPC) proposed by [Liu et al., 2022a], and the WPC2.0 database [Liu et al., 2021a] for validation.
Dataset Splits Yes The k-fold cross validation strategy is employed for the experiment to accurately estimate the performance of the proposed method. Since the SJTU-PCQA, WPC, and WPC2.0 contain 9, 20, 16 groups of point clouds respectively, 9-fold, 5-fold, and 4-fold cross validation is selected for the three database to keep the train-test ratio around 8:2.
Hardware Specification No The paper does not provide specific details regarding the hardware used for experiments (e.g., GPU models, CPU types, or memory).
Software Dependencies No The paper mentions specific optimizers (Adam) and neural network architectures (Point Net++, ResNet50) and databases (ImageNet), but does not specify software versions for libraries, frameworks, or programming languages (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes The Adam optimizer [Kingma and Ba, 2015] is utilized with weight decay 1e-4, the initial learning rate is set as 5e-5, and the batch size is set as 8. The model is trained for 50 epochs by default. Specifically, We set the point cloud sub-model size Ns as 2048, set the number of sub-models Nδ = 6, and set the number of image projections NI = 4. [...] The multi-head attention module employs 8 heads and the feed-forward dimension is set as 2048. The weights λ1 and λ2 for LMSE and Lrank are both set as 1.