MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
Authors: Zengyi Qin, Jinglu Wang, Yan Lu8851-8858
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on the challenging KITTI dataset demonstrate that our network outperforms the state-of-art monocular method in 3D object localization with the least inference time. |
| Researcher Affiliation | Collaboration | Tsinghua University, Microsoft Research {v-zeqin, jinglwa, yanlu}@microsoft.com |
| Pseudocode | No | The paper describes the approach conceptually but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code or a link to a code repository for the methodology described. |
| Open Datasets | Yes | We evaluate the proposed network on the challenging KITTI dataset (Geiger, Lenz, and Urtasun 2012), which contains 7481 training images and 7518 testing images with calibrated camera parameters. |
| Dataset Splits | Yes | For a fair comparison, we use the train1/val1 split following the setup in (Chen et al. 2016; 2017), where each set contains half of the images. |
| Hardware Specification | Yes | The network is trained using a single GPU of NVidia Tesla P40. The inference time achieves about 0.06 seconds per image on a Geforce GTX Titan X |
| Software Dependencies | No | The paper mentions software components and optimizers (e.g., VGG-16, Kitti Box, Adam optimizer) but does not provide specific version numbers for any programming languages, libraries, or frameworks used. |
| Experiment Setup | Yes | In the loss functions, we set ω = α = β = 10. L2 regularization is applied to the model parameters with a decay rate of 1e-5. We first train the 2D detector, along with the backbone, for 120K iterations using the Adam optimizer (Kingma and Ba 2015). Then the 3D reasoning modules, IDE, 3D localization and local corners, are trained for 80K iterations with the Adam optimizer. Finally, we use SGD to optimize the whole network in an end-to-end fashion for 40K iterations. The batch-size is set to 5, and the learning rate is 1e-5 throughout training. |