Fast Preprocessing for Robust Face Sketch Synthesis
Authors: Yibing Song, Jiawei Zhang, Linchao Bao, Qingxiong Yang
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments using state-of-the-art face sketch synthesis methods including MRF [Wang and Tang, 2009], RMRF [Zhang et al., 2010], MWF [Zhou et al., 2012] and SSD [Song et al., 2014]. The focus is to demonstrate the improvement after integrating BLR into existing methods. The experiments are conducted on the benchmarks including CUHK [Wang and Tang, 2009], AR [Aleix and Robert, 1998], and FERET datasets [Zhang et al., 2011]. |
| Researcher Affiliation | Collaboration | Yibing Song1, Jiawei Zhang1, Linchao Bao2, and Qingxiong Yang3 1City University of Hong Kong 2Tencent AI Lab 3University of Science and Technology of China |
| Pseudocode | No | The paper describes the proposed algorithm in text and mathematical equations, but does not provide pseudocode or a clearly labeled algorithm block. |
| Open Source Code | No | No explicit statement or link providing concrete access to the source code for the methodology described in this paper was found. |
| Open Datasets | Yes | The experiments are conducted on the benchmarks including CUHK [Wang and Tang, 2009], AR [Aleix and Robert, 1998], and FERET datasets [Zhang et al., 2011]. |
| Dataset Splits | No | The paper mentions splitting the CUHK dataset into '88 training photo-sketch pairs and 100 input pairs' and performing 'Cross-Dataset Experiments' using CUHK as training and AR as input. However, it does not explicitly define or refer to a distinct 'validation' dataset or split for hyperparameter tuning or model selection. |
| Hardware Specification | Yes | Table 1 shows the runtime of existing methods to process a CUHK input image (obtained from a 3.4GHz Intel i7 CPU). |
| Software Dependencies | No | The paper mentions several algorithms and methods like CLAHE, matting algorithm, and facial landmark detection, but it does not specify version numbers for any software dependencies or libraries used in the implementation. |
| Experiment Setup | No | The paper describes how synthetic data was generated by adjusting luminance using scalars (σF and σB) and outlines the steps for handling side lighting and pose variance. It also mentions pre-computation of facial landmarks and alpha mattes. However, it does not provide specific hyperparameter values (e.g., learning rates, batch sizes, number of epochs) for the sketch synthesis models or explicit training configuration settings beyond the core algorithm description. |