Learning to Hallucinate Face Images via Component Generation and Enhancement
Authors: Yibing Song, Jiawei Zhang, Shengfeng He, Linchao Bao, Qingxiong Yang
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experiments demonstrate that our method performs favorably against state-of-the-art methods. |
| Researcher Affiliation | Collaboration | Yibing Song1, Jiawei Zhang1, Shengfeng He2, Linchao Bao3, and Qingxiong Yang4 1City University of Hong Kong 2South China University of Technology 3Tencent AI Lab 4University of Science and Technology of China |
| Pseudocode | No | The paper provides a pipeline diagram (Figure 2) and describes the algorithm steps in text, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | Footnote 1 states: 'Complete experimental results and our implementation are provided on the authors webpage.' However, no specific URL or repository link is provided, making it not concrete access. |
| Open Datasets | Yes | We conduct experiments on four datasets: Multi-PIE [Gross et al., 2010] frontal, Multi-PIE pose, Pub Fig [Kumar et al., 2009] and Multi-PIE HR datasets. |
| Dataset Splits | No | The paper specifies training and testing data (e.g., '2184 images are taken as training and 342 images are taken as input' and 'adopt leave-one-out strategy'), but it does not explicitly mention a separate 'validation' dataset split for hyperparameter tuning or early stopping. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory, cloud resources) used to run the experiments. |
| Software Dependencies | No | The paper mentions using CNNs and refers to SRCNN [Dong et al., 2015] for network structure and training process, but it does not specify any software dependencies with version numbers (e.g., Python, PyTorch/TensorFlow, CUDA versions). |
| Experiment Setup | No | The paper states, 'The network structure and training process are similar with those of SRCNN [Dong et al., 2015]', but it does not explicitly provide specific hyperparameter values (e.g., learning rate, batch size, epochs) or detailed training configurations within the text. |