UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors designed a new fast method to brighten and improve very detailed, dark images without using heavy computer power. They break down images into simple parts and use a special math tool called Clifford algebra to better combine image details while reducing noise. Their approach adjusts brightness in a realistic way based on how we see light and runs very quickly even on normal devices. Tests show it works better than current leading methods for fixing dark ultra-high-definition images.
ultra-high-definition (UHD)low-light image restorationClifford algebrafeature pyramiddepthwise separable convolutionU-NetRetinex theorymixed-precision computationdynamic operator fusionimage enhancement
Authors
Xiaohan Wang, Chen Wu, Dawei Zhao, Guangwei Gao, Dianjie Lu, Guijuan Zhang, Linwei Fan, Xu Lu, Shuai Wu, Hang Wei, Zhuoran Zheng
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.