PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
Authors: Yujia Liu, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner
ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We validate the proposed model on a publicly available synthetic dataset, for which the ground truth wireframes are accessible, as well as on a new real-world dataset. Our model produces wireframe abstractions of good quality and outperforms several baselines. |
| Researcher Affiliation | Academia | Yujia Liu, Stefano D Aronco, Konrad Schindler, Jan Dirk Wegner Eco Vision Lab, Photogrammetry and Remote Sensing, ETH Zürich {firstname.lastname}@geod.baug.ethz.ch |
| Pseudocode | No | The paper describes the architecture and its components in detail but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We validate PC2WF with models from the publicly available ABC dataset of CAD models, and with a new furniture dataset collected from the web. The ABC dataset references Koch et al. (2019). |
| Dataset Splits | Yes | It consists of 3,000 samples, which we randomly split into 2,000 for training, 500 for validation, and 500 for testing. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models, memory, or cloud service specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'Fully Convolutional Geometric Features (FCGF, Choy et al., 2019b)' and 'sparse tensors (Choy et al., 2019a)' as components of their backbone, but it does not specify version numbers for any software dependencies or frameworks. |
| Experiment Setup | No | The paper describes the overall training process, including the joint loss function and sampling strategies for edge detection, but it does not specify concrete hyperparameter values such as learning rate, batch size, number of epochs, or optimizer settings used in the experiments. |