Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs
Authors: Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate that our method outperforms state-of-the-art methods and can produce high-quality demoiréd results. Quantitative and qualitative experimental results on both public and our datasets show that our model outperforms state-of-the-art methods. |
| Researcher Affiliation | Collaboration | Lin Liu1,2 Shanxin Yuan2 Jianzhuang Liu2 Liping Bao1 Gregory Slabaugh2 Qi Tian3 1EEIS Department, University of Science and Technology of China 2Noah s Ark Lab, Huawei Technologies 3Huawei Cloud BU |
| Pseudocode | No | The paper describes the optimization algorithm and network structure in text and diagrams but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | For the screen moiré patterns, the data are sampled from TIP2018 dataset [39], from which we randomly choose 130 image pairs (moiré images and moiré-free images). In addition, we build a new moiré dataset, including images with screen and texture moiré artifacts. As far as we know, this is the first dataset with real texture moiré patterns. |
| Dataset Splits | No | The paper mentions using synthetic and real datasets, and selects subsets for evaluation (e.g., 'randomly choose 25 images and 38 images' for real data). It discusses training existing supervised models on TIP2018 and MITMoire. However, it does not provide explicit training, validation, and test dataset splits (e.g., percentages or specific sample counts for each split) for its own experiments to ensure reproducibility of data partitioning. |
| Hardware Specification | Yes | The experiments are conducted on a NVIDIA RTX 2080Ti GPU. |
| Software Dependencies | Yes | Our algorithm is implemented in Pytorch. An off-the-shelf trained algorithm (MATLAB2018b) is used to obtain the NIQE and BRISQUE scores. |
| Experiment Setup | Yes | The initial learning rate is set to 0.01 and reduced by a half for every 500 iterations. The algorithm runs for 3000 iterations for each image pair. |