UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion

TL;DR

This paper introduces a real-time UHD low-light image enhancement network using Clifford algebra for feature fusion, achieving millisecond inference on edge devices and outperforming existing models.

Contribution

A novel geometric feature fusion method based on Clifford algebra enables efficient, high-quality low-light image enhancement suitable for real-time edge device deployment.

Findings

Achieves millisecond inference on 4K/8K images with a single device.

Outperforms state-of-the-art models on multiple restoration metrics.

Uses Clifford algebra for effective noise suppression and texture preservation.

Abstract

Considering efficiency, ultra-high-definition (UHD) low-light image restoration is extremely challenging. Existing methods based on Transformer architectures or high-dimensional complex convolutional neural networks often suffer from the "memory wall" bottleneck, failing to achieve millisecond-level inference on edge devices. To address this issue, we propose a novel real-time UHD low-light enhancement network based on geometric feature fusion using Clifford algebra in 2D Euclidean space. First, we construct a four-layer feature pyramid with gradually increasing resolution, which decomposes input images into low-frequency and high-frequency structural components via a Gaussian blur kernel, and adopts a lightweight U-Net based on depthwise separable convolution for dual-branch feature extraction. Second, to resolve structural information loss and artifacts from traditional high-low frequency feature fusion, we introduce spatially aware Clifford algebra, which maps feature tensors to a multivector space (scalars, vectors, bivectors) and uses Clifford similarity to aggregate features while suppressing noise and preserving textures. In the reconstruction stage, the network outputs adaptive Gamma and Gain maps, which perform physically constrained non-linear brightness adjustment via Retinex theory. Integrated with FP16 mixed-precision computation and dynamic operator fusion, our method achieves millisecond-level inference for 4K/8K images on a single consumer-grade device, while outperforming state-of-the-art (SOTA) models on several restoration metrics.