Enhancing Deep Image Prior with Multiscale Attention, SVD Pooling, and Preconditioned Optimizers for Image Processing

Abstract

Deep Image Prior (DIP) is effective in recovering high-quality images in inverse problems such as restoration and MRI, but it often suffers from overfitting and spectral bias. To address these challenges, we introduce a novel DIP-based architecture that integrates enhanced SVD pooling to preserve global contextual features, Softplus activation to ensure smooth and stable gradient propagation, and multiscale attention mechanisms with dilated convolutions to effectively recover fine image details. To further accelerate training and enhance generalization, we adopt advanced preconditioned optimizers such as DiffGrad and Apollo. Our data-independent restoration strategy is thoroughly evaluated on image denoising and inpainting benchmarks, yielding notable improvements in MSE, PSNR, and SSIM. We supplement our quantitative results with rich visualizations, including side-by-side restoration outputs, SSIM/PSNR trends over epochs, 3D visualizations of dominant neuron activations, and comparative 3D bar plots illustrating optimizer performance. The source code for all the simulations conducted in this paper is available at the following link: \url{https://github.com/israrjamali/DIP-SVD-Code-for-Image-Denoising-and-Inpainting}