An Energy-Efficient Image Deblurring Accelerator with Quad-base-Quad-scale Quantized Format and Layer Normalization-aware Optimization

Abstract

An energy-efficient novel data-format-based image deblurring accelerator is proposed for mobile cameras. As the demand for photography in dynamic environments continues to grow and the limitations of physical stabilization are tightening, post-processing methods to restore sharp images have gained increasing attention, notably deblurring methods based on convolutional neural networks. However, their heavy computational cost hinders their integration into mobile computing platforms. The proposed accelerator enables energy-efficient acceleration of deblurring through the following three key features: 1) A Quad-base-Quad-scale Quantized format that maintains image quality with only 8-bit, reducing external memory access (EMA) by 33% and achieving 75.7% higher multiply-and- accumulation (MAC) energy efficiency compared to conventional 12-bit precision; 2) A dual-stationary systolic array architecture that selects the optimal dataflow for each UNet block based on processing element (PE) utilization; 3) A Layer Normalization-Aware Optimization technique, enabling parallel normalization and fusion of affine transformation. As a result, the proposed accelerator achieves 2.49 TOPS/W, which is 2.23× higher than prior work, enabling energy-efficient deblurring for mobile applications. Keywords: Image deblurring, quantization, dual-stationary dataflow, energy-efficient, hardware accelerator.