QFormer: An Efficient Quaternion Transformer for Image Denoising

Authors: Bo Jiang, Yao Lu, Guangming Lu, Bob Zhang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments demonstrate that the proposed QFormer produces state-of-the-art results in both denoising performance and efficiency.
Researcher Affiliation Academia Bo Jiang1 , Yao Lu2 , Guangming Lu2 and Bob Zhang3 1College of Mechanical and Electronic Engineering, Northwest A&F University, China 2Department of Computer Science, Harbin Institute of Technology at Shenzhen, China 3Department of Computer and Information Science, University of Macau, China
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, such as a specific repository link or explicit code release statement.
Open Datasets Yes Table 1: Average PSNR and SSIM of the denoised real images from Nam, Poly U and SIDD datasets.
Dataset Splits No The paper mentions using Nam, Poly U, and SIDD datasets but does not provide specific details on train/validation/test splits, exact percentages, or sample counts for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models or processor types) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment.
Experiment Setup No The paper mentions architectural parameters like feature channels (C=16, 32, 44) and QTB depth (N=2), but does not provide specific experimental setup details such as learning rates, batch sizes, or optimizer settings.