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

2026-04-10

AI Summary

This work addresses the challenge of real-time ultra-high-definition low-light image enhancement on edge devices, which is hindered by the "memory wall" bottleneck. The authors propose an efficient architecture that constructs a four-level progressive-resolution feature representation via Gaussian pyramid decomposition and employs a lightweight depthwise-separable convolutional U-Net for dual-branch high- and low-frequency feature extraction. Notably, this is the first study to incorporate 2D Clifford algebra into this task, mapping features into a multivector space and leveraging Clifford similarity to jointly preserve structural details and suppress noise. Furthermore, guided by Retinex theory, the method generates adaptive Gamma and Gain maps to perform physically constrained nonlinear luminance adjustment. The proposed approach enables millisecond-level processing of 4K/8K images on a single consumer-grade device and outperforms state-of-the-art models across multiple quantitative metrics.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Non-convex Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• UHD low-light image enhancement
• real-time inference
• memory wall
• edge devices
• image restoration

Innovation

• Clifford algebra
• real-time UHD enhancement
• feature fusion
• low-light image restoration
• depthwise separable convolution