AI Paper Atlas

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

NeurIPS 2025 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 0 citations (OpenAlex)

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy