Research map / Architectures and efficiency / Spiking networks
Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural Networks
Hongzhi Wang, Xiubo Liang, Jinxing Han, Weidong Geng
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Spike-RetinexFormer, a low-light image enhancement architecture that combines Retinex theory, spiking neural networks, and a Transformer to reduce energy and memory cost.
Problem
Low-light image enhancement methods often neglect computational efficiency, incurring high energy and memory costs.
Approach
Integrates Retinex-based decomposition, spiking neural networks, and a Transformer backbone into one LLIE architecture so that enhancement runs in an energy-efficient spiking manner.
Experimental setup
Builds on: RetinexFormer
Closest papers by meaning
- IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective (AAAI 2025 · similarity 0.91)
- Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023 · similarity 0.90)
- MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space (NeurIPS 2024 · similarity 0.87)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.87)
- Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation (AAAI 2025 · similarity 0.87)
- Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
