Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Distribution Aware VoteNet for 3D Object Detection

Authors: Junxiong Liang, Pei An, Jie Ma1583-1591

AAAI 2022 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on both Scan Net V2 and SUN RGB-D datasets demonstrate that the proposed DAVNet achieves significant improvement and outperforms state-of-the-art 3D detectors.
Researcher Affiliation Academia Huazhong University of Science and Technology EMAIL
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statements about releasing open-source code or links to a code repository.
Open Datasets Yes We evaluate our network on Scan Net V2 (Dai et al. 2017) and SUN RGB-D (Song, Lichtenberg, and Xiao 2015).
Dataset Splits No The paper mentions 'SUN RGB-D validation set' and 'Scan Net V2 validation set' but does not provide specific details on the train/validation/test split percentages or sample counts.
Hardware Specification Yes We conduct all our training on one GTX1080Ti GPU.
Software Dependencies No The paper mentions using an 'Adam optimizer' but does not specify version numbers for any software, libraries, or frameworks used for implementation.
Experiment Setup Yes We use an Adam optimizer to train our model in batch size 8 for both datasets. For Scan Net V2, the network is trained for 180 epochs. The learning rate is initialized as 0.01 and decreased by 10 after 120 and 160 epochs. For SUN RGBD, we train for 200 epochs with a learning rate initialized as 0.001. It is decreased by 10 after 120, 160, and 180 epochs.