Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis
Authors: Haoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate that the proposed Soft-Gated Warping-GAN significantly outperforms the existing state-of-the-art methods on pose-based person image synthesis both qualitatively and quantitatively, especially for large pose variation. Additionally, human perceptual study further indicates the superiority of our model that achieves remarkably higher scores compared to other methods with more realistic generated results. |
| Researcher Affiliation | Academia | 1School of Data and Computer Science, Sun Yat-sen University 2Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou 510006, P.R.China 3School of Intelligent Systems Engineering, Sun Yat-sen University 4School of Computer Science, South China Normal University |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled 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 described methodology. |
| Open Datasets | Yes | Deep Fashion [36] consists of 52,712 person images... We select 81,414 pairs as our training set and randomly select 12,800 pairs for testing. Market-1501 [34] contains 322,668 images... Then we also randomly select 12,800 pairs as the test set and 296,938 pairs for training. ...we use the LIP [9] dataset to train a human parsing network. |
| Dataset Splits | No | The paper specifies train and test splits for Deep Fashion and Market-1501 datasets, but does not explicitly mention a separate validation split or its size for the main experiments. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using the Adam optimizer and adapting from pix2pix HD, but it does not specify version numbers for any software dependencies, programming languages, or libraries. |
| Experiment Setup | Yes | We use the Adam [16] optimizer and set β1 = 0.5, β2 = 0.999. We use learning rate of 0.0002. We use batch size of 12 for Deepfashion, and 20 for Market-1501. |