A Condition Number for Joint Optimization of Cycle-Consistent Networks
Authors: Leonidas J. Guibas, Qixing Huang, Zhenxiao Liang
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on benchmark datasets justify the effectiveness of our approach for optimizing dense correspondences between 3D shapes and neural networks for predicting dense image flows. |
| Researcher Affiliation | Academia | Leonidas Guibas1, Qixing Huang2, and Zhenxiao Liang2 1Stanford University 2The University of Texas at Austin |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described, such as a specific repository link or an explicit code release statement. |
| Open Datasets | Yes | The evaluation considers two shape collections from Shape Co Seg [42]: Alien (200 shapes) and Vase (300 shapes). We perform experimental evaluation on 12 rigid categories from PASCAL3D [43]. |
| Dataset Splits | No | The paper uses datasets for training and evaluation but does not provide specific details on how the datasets were split into training, validation, and test sets with exact percentages or sample counts. |
| Hardware Specification | No | The paper mentions "a hardware Donation from NVIDIA" in the acknowledgements but does not provide specific details such as exact GPU/CPU models, processor types, or memory used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | Yes | For numerical optimization, we start from the identity map Xij = Im, (i, j) E and apply steepest descent with exact line search [30]. We run 3000 iteration on each dataset. In our experiments, we generate V by first picking the dominant view of each category [43] and then sampling a grid of 5 x 5 camera poses. This grid is centered at the dominant view, its two axes align with the latitude and longitude, and its spacing is 22.5 degrees. |