Digital image super-resolution reconstruction method based on stochastic gradient descent algorithm

Abstract

Digital image super-resolution (SR) techniques have gained significant attention in computational imaging for reconstructing high-quality images from low-resolution inputs. Traditional SR methods often struggle with preserving fine details, texture consistency, and edge sharpness while maintaining computational efficiency, limiting their practical applications in real-time systems. The research proposes an Adaptive Dynamic Efficient Parameter Tuning for Super-Resolution (ADEPT-SR) framework based on an optimized stochastic gradient descent (SGD) algorithm. The technique transforms low-resolution (LR) images into high-resolution (HR) counterparts, addressing fundamental limitations in imaging hardware. ADEPT-SR implements an adaptive SGD framework with momentum-based parameter optimization to minimize reconstruction error between predicted and ground-truth HR images. The key innovation in ADEPT-SR lies in a hybrid loss function combining structural similarity index measure (SSIM) and perceptual loss with dynamic weighting that adjusts during training iterations. The approach enables superior edge preservation and texture reconstruction compared to conventional methods. An adaptive learning rate schedule dynamically responds to local optimization landscapes, reducing convergence time by 37 % while avoiding local minima. ADEPT-SR offers significant applications in medical imaging, satellite imagery analysis, surveillance systems, and consumer electronics, where hardware limitations constrain native resolution. Experimental validation across standard benchmark datasets demonstrates that ADEPT-SR achieves a peak signal-to-noise ratio (PSNR) improvement of 1.8 dB over standard bicubic interpolation and 0.7 dB over recent deep learning approaches for a 4 × upscaling factor. The method reduces computational complexity by 43 % compared to deep learning methods while maintaining visual quality improvement.