Problem
Research questions and friction points this paper is trying to address.
Spiking Neural Networks
Image Restoration
Receptive Field Limitation
Long-range Dependency
Wavelet Domain
Spiking Pyramid Wavelet Transformation for High-efficient and Low-energy Image Restoration
🤖 AI Summary
This work addresses the limitations of conventional spiking convolutional neural networks (SCNNs), which struggle to effectively model long-range dependencies in image restoration due to their restricted receptive fields while maintaining energy efficiency. To overcome this, the study introduces, for the first time, a pyramid wavelet architecture into spiking neural networks, proposing the Spiking Pyramid Wavelet Model (SPWM). The core innovation lies in a spiking dual-pyramid wavelet module that jointly captures degradation characteristics and long-range dependencies in the wavelet domain. This approach transcends the receptive field constraints of traditional SNNs, achieving significantly reduced computational costs and energy consumption across multiple image restoration benchmarks, all while preserving superior reconstruction quality.
📝 Abstract
Spiking neural networks (SNNs) have garnered significant interest in computer vision due to their potential for efficiency and biological inspiration. While spiking CNN-based methods have shown promise for image restoration (IR) tasks, their performance is constrained by the inherent receptive field limitations of CNN operations. In the paper, we explore the benefits of discrete wavelet transformation and propose a spiking pyramid wavelet-based model (SPWM) for high-efficient and low-energy target. Specifically, we develop a spiking dual pyramid wavelet (SDPW) block to model long-range dependency and exploit the properties of the degradation in the wavelet domain. Experimental results on several benchmarks demonstrate that SPWM significantly lowers computational costs and energy consumption while maintaining image quality. Our method showcases the potential of SNNs in the field of IR, offering new insights for future applications of resource-limited devices.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Spiking Neural Networks
Wavelet Transform
Image Restoration
Low-energy Computing
Pyramid Architecture
🔎 Similar Papers
No similar papers found.
