MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation

Authors: Yunsong Zhou, Quan Liu, Hongzi Zhu, Yunzhe Li, Shan Chang, Minyi Guo

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on the realworld KITTI dataset. The results demonstrate that Mo GDE can effectively improve the Mono3D accuracy and robustness for both near and far objects. Mo GDE yields the best performance compared with the state-of-the-art methods by a large margin and is ranked number one on the KITTI 3D benchmark.
Researcher Affiliation Academia 1Shanghai Jiao Tong University 2Donghua University {zhouyunsong,liuquan2017,hongzi,yunzhe.li,guo-my}@sjtu.edu.cn changshan@dhu.edu.cn
Pseudocode No The paper describes the system architecture and components (e.g., Figure 2, equations), but it does not include any pseudocode or algorithm blocks.
Open Source Code No The whole suite of the code base will be released and the experimental results will be posted to the public leaderboard.
Open Datasets Yes We conduct experiments on the widely-adopted KITTI3D dataset and KITTI Odometry dataset [17]. ... Andreas Geiger, Philip Lenz, and Raquel Urtasun. Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
Dataset Splits No The paper mentions evaluating on the "KITTI val set" (Table 2, Table 3, Table 4) but does not provide specific details on the split percentages or sample counts for training, validation, and test sets in the main text.
Hardware Specification No The paper does not explicitly describe the hardware (e.g., specific GPU/CPU models, memory, or cloud instances) used for running the experiments in the main text.
Software Dependencies No The paper mentions using specific models like DLA-34 and GUPNet, but does not provide specific version numbers for software dependencies (e.g., Python, PyTorch, TensorFlow, CUDA versions) needed for reproducibility.
Experiment Setup No The paper describes the overall architecture of Mo GDE and its components (e.g., using DLA-34 backbone), but it does not specify concrete experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) in the main text.