BM3D vs 2-Layer ONN
This addresses the need for efficient denoising methods in resource-constrained scenarios, though it is incremental as it builds on existing neural network variants.
The study tackled the problem of image denoising by comparing compact neural networks to the BM3D method, finding that a two-layer self-organized operational neural network (Self-ONN) achieves competitive results with BM3D and surpasses it significantly at high noise levels.
Despite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs. Older but computationally more efficient methods such as BM3D remain a popular choice, especially in resource-constrained scenarios. In this study, we aim to find out whether compact neural networks can learn to produce competitive results as compared to BM3D for AWGN image denoising. To this end, we configure networks with only two hidden layers and employ different neuron models and layer widths for comparing the performance with BM3D across different AWGN noise levels. Our results conclusively show that the recently proposed self-organized variant of operational neural networks based on a generative neuron model (Self-ONNs) is not only a better choice as compared to CNNs, but also provide competitive results as compared to BM3D and even significantly surpass it for high noise levels.