New AI Framework Dramatically Improves Photos Taken in Near-Darkness
Researchers have developed an AI system that enhances low-light images while preserving detail and controlling noise—a capability critical for autonomous vehicles, surveillance, and mobile devices. By embedding physics-based noise detection into a machine learning model, the framework achieves better results faster than existing methods, potentially unlocking new applications in robotics and visual inspection.
Originaltitel: Fusing physical priors and visual mamba: An SNR-Aware framework for low-Light enhancement in HVI space
<p>Low-light image enhancement (LLIE) is a prerequisite for robust visual perception in multi-source information fusion systems. However, simultaneously achieving high-fidelity restoration, effective noise management, and computational efficiency remains a formidable challenge. To address this, we propose PPMNet (Physical Priors Mamba Network), a novel framework that synergizes physical priors with the Mamba architecture within the HVI (Horizontal/Vertical Intensity) domain. Central to our methodology is the Physics-based Signal-to-Noise Ratio (SNR) Estimation Module (PSEM), which explicitly models Poisson-Gaussian noise statistics to derive a pixel-wise reliability map. Unlike black-box models, we utilize this map as a dynamic gating signal in our proposed SNR-Aware Mamba Block. This mechanism transforms the generic state transition into a physically interpretable process, adaptively preserving long-range dependencies in signal-dominant regions while filtering out corruption in noise-dominant areas. Furthermore, we design a dual-branch architecture that implements distinct "hard suppression" and "soft gating" strategies for chromaticity and intensity, effectively resolving the conflict between denoising and detail preservation. Extensive experiments on multiple benchmarks demonstrate that PPMNet significantly outperforms state-of-the-art methods, particularly under extreme low-light conditions. Specifically, on the LOL-v2-Real dataset, our method achieves a 0.62 dB PSNR improvement over the recent HVI-based method, while maintaining a linear computational complexity suitable for real-time applications.</p>