Neural Sparse Representation for Image Restoration
This work addresses efficiency and performance challenges in image restoration tasks like super-resolution and denoising, offering an incremental improvement by integrating sparsity into existing network architectures.
The paper tackles the problem of improving deep neural networks for image restoration by structurally enforcing sparsity constraints on hidden neurons, resulting in computation savings without accuracy loss and enhanced model capacity with negligible extra cost.
Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. The sparsity constraints are favorable for gradient-based learning algorithms and attachable to convolution layers in various networks. Sparsity in neurons enables computation saving by only operating on non-zero components without hurting accuracy. Meanwhile, our method can magnify representation dimensionality and model capacity with negligible additional computation cost. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks, including image super-resolution, image denoising, and image compression artifacts removal. Code is available at https://github.com/ychfan/nsr