Unsupervised Depth Estimation, 3D Face Rotation and Replacement
Authors: Joel Ruben Antony Moniz, Christopher Beckham, Simon Rajotte, Sina Honari, Chris Pal
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 3 Experiments 3.1 Depth Net Evaluation on Paired Faces Table 1: (left) Comparing the Mean Squared Error (MSE) and MSE normalized by inter-ocular distance (MSE_norm) of different models. |
| Researcher Affiliation | Collaboration | 1Carnegie Mellon University, 2Mila-University of Montreal, 3Polytechnique Montreal, 4Element AI |
| Pseudocode | No | The paper describes the approach and architecture using text and diagrams (Figure 1) but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | Code will be released at: https://github.com/joelmoniz/Depth Nets/ (This indicates future release, not concrete access at the time of publication.) |
| Open Datasets | Yes | For the experiments in this section, we use a subset of the VGG dataset [16], with training and validating on all possible pairs of images belonging to the same identity for 2401 identities. This yields 322,227 train and 43,940 validation pairs. We use the 3DFAW dataset [14; 26; 6] that contains 66 3D keypoints to facilitate comparing with ground truth (GT) depth. |
| Dataset Splits | Yes | For the experiments in this section, we use a subset of the VGG dataset [16], with training and validating on all possible pairs of images belonging to the same identity for 2401 identities. This yields 322,227 train and 43,940 validation pairs. It provides 13,671 train and 4,500 valid images. |
| Hardware Specification | No | The paper acknowledges 'Compute Canada and Calcul Quebec for providing computational resources' but does not specify exact GPU/CPU models, memory, or other specific hardware configurations used for experiments. |
| Software Dependencies | No | The paper describes the architectural components and methods but does not provide specific software dependencies or version numbers for libraries, frameworks, or other tools used. |
| Experiment Setup | No | The paper states 'Check experimental setup details in Supplementary.', but these details are not provided in the main paper text. Thus, specific hyperparameters or training settings are not explicitly detailed here. |