Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Implicit Prompt Learning for Image Denoising
Authors: Yao Lu, Bo Jiang, Guangming Lu, Bob Zhang
IJCAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on multiple benchmarks showed that the proposed IPLID achieves competitive results with only 1 percent of pre-trained backbone parameters, outperforming classical denoising methods in both efficiency and quality of restored images. |
| Researcher Affiliation | Academia | 1Department of Computer Science, Harbin Institute of Technology at Shenzhen, China 2College of Mechanical and Electronic Engineering, Northwest A&F University, China 3Department of Computer and Information Science, University of Macau, China |
| Pseudocode | No | The paper presents figures for block structures and mathematical equations but does not include any section or figure explicitly labeled 'Pseudocode' or 'Algorithm'. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code or a link to a code repository. |
| Open Datasets | Yes | Table 1 presents the denoising results of the proposed IPLID on real noisy images from the SIDD [Abdelhamed et al., 2018], Poly U [Xu et al., 2018], and Nam [Nam et al., 2016] datasets. |
| Dataset Splits | No | The paper mentions using datasets like SIDD, Poly U, and Nam, and refers to DIV2K and BSD400 for fine-tuning, but does not provide explicit training/validation/test splits (e.g., percentages or sample counts) for the experiments conducted. |
| Hardware Specification | Yes | To ensure equitable comparisons of efficiency, we utilize FLOPs, inference time, and trainable parameters as metrics. In particular, we perform the comparisons on identical computer equipment (i.e., an Nvidia RTX Titan GPU) for efficiency. |
| Software Dependencies | No | The paper mentions using the 'Adam optimizer' but does not provide specific version numbers for software dependencies or libraries (e.g., PyTorch, TensorFlow, CUDA versions). |
| Experiment Setup | Yes | We use the Adam [Loshchilov and Hutter, 2017] optimizer to train our IPLID with setting β1 and β2 to 0.9 and 0.999, respectively. The learning rate is set to 1 10 4 in training. |