Generative Adaptive Convolutions for Real-World Noisy Image Denoising

Authors: Ruijun Ma, Shuyi Li, Bob Zhang, Zhengming Li1935-1943

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate the superior denoising performances of the proposed FADNet versus the state-of-the-art. In contrast to the existing deep denoisers, our FADNet is not only flexible and efficient, but also exhibits a compelling generalization capability, enjoying tremendous potential for practical usage.
Researcher Affiliation Academia Ruijun Ma1, 2, Shuyi Li1, Bob Zhang1 , Zhengming Li2 1 PAMI Research Group, Department of Computer and Information Science, University of Macau 2 Guangdong Industrial Training Center, Guangdong Polytechnic Normal University
Pseudocode No The paper describes the network architecture and method steps but does not include formal pseudocode or an algorithm block.
Open Source Code No The paper does not provide any explicit statement about open-source code availability or a link to a code repository.
Open Datasets Yes In this work, the training data was from SIDD (Abdelhamed, Lin, and Brown 2018).
Dataset Splits Yes SIDD also provided a medium version package, in which 320 images pairs were leveraged for fast training and 1280 images pairs for validation purposes.
Hardware Specification Yes All the experiments were carried out using the Pytorch library (Paszke et al. 2019) on a machine with an NVIDIA Titan Xp GPU.
Software Dependencies No The paper mentions PyTorch and Adam optimizer but does not provide specific version numbers for these software components.
Experiment Setup Yes We utilized the Adam optimizer (Kingma and Ba 2014) to update the network, with β1 = 0.7, β2 = 0.999, and ϵ = 10 8. The learning rate was initially set as 0.001 and reduced to 0.0001 when the training errors held steady.