A Large-Scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement
Authors: Zinuo Li, Xuhang Chen, Shuqiang Wang, Chi-Man Pun
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments reveal that the performance of our model is superior than state-of-the-art techniques. |
| Researcher Affiliation | Academia | 1University of Macau 2Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences |
| Pseudocode | No | The paper describes the proposed method in detail and provides a network architecture diagram (Figure 3), but it does not include any pseudocode or algorithm blocks. |
| Open Source Code | Yes | The link of code and data is https://github.com/CXH-Research/Film Net. |
| Open Datasets | Yes | Datasets In this section, three datasets are used for training and evaluation in total: MIT-Adobe Five K [Bychkovsky et al., 2011], HDR+ [Hasinoff et al., 2016] and our Film Set. |
| Dataset Splits | No | It is configured with 4657 training samples and 638 testing samples. For easier training and validation, all images are transformed to 512 512 resolution and standard PNG format. For Five K and HDR+, we use the same dataset configuration as [Zeng et al., 2020] and transform all images to the more common 480p resolution and standard PNG format. |
| Hardware Specification | Yes | The typical Adam optimizer with its default parameters is used to train our model by NVIDIA RTX A6000. |
| Software Dependencies | No | Our implementation is based on the Py Torch. The paper mentions PyTorch but does not specify a version number or other software dependencies with versions. |
| Experiment Setup | Yes | The batch size is set to 1 and the learning rate is set to 1e 4. Random cropping, horizontal flipping, and tweaks to brightness and saturation are used to enrich data. |