Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion

Authors: Zhaoxin Fan, Yulin He, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on multiple datasets show that Ra PD outperforms previous methods in both homologous and heterologous scenarios.
Researcher Affiliation Collaboration Zhaoxin Fan1 , Yulin He1 , Zhicheng Wang3 , Kejian Wu3 , Hongyan Liu2 , Jun He1 1Renmin University of China 2Tsinghua University 3Nreal
Pseudocode No The paper does not contain explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding open-source code for the described methodology.
Open Datasets Yes To verify the superiority of Ra PD, we conduct experiments on three widely used public datasets: MVP [Pan et al., 2021], CRN [Wang et al., 2020a] and KITTI [Geiger et al., 2013].
Dataset Splits No We train all models on the MVP training set and test them on the MVP testing set. [...] 1% to 10% are the percentages of paired point clouds in the training set that are used for training.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as GPU models, CPU models, or memory specifications.
Software Dependencies No The paper does not provide specific software dependency details with version numbers (e.g., 'Python 3.8, PyTorch 1.9, and CUDA 11.1').
Experiment Setup Yes We set our encoder-decoder network architecture to be the same as PCN [Yuan et al., 2018] for a fair comparison. The architecture of the discriminator follows the basic architecture of [Li et al., 2019]. The evaluation metrics are chamfer distance (CD) and the F1 score, following [Pan et al., 2021]. More details please refer to the Supp Mat. [...] L = λ1Lz,paired + λ2Lz,unpaired + λ3 Lcd,paired + λ4Lcd,unpaired + λ5Lg (7) where λ1 to λ5 are balance terms. For the discriminator, it is optimized using Ld independently.