NEC-Diff：面向极端黑暗运动场景的噪声鲁棒事件-RAW 互补扩散模型
NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness
对做低光照成像与事件相机融合的研究者，这篇提供了两个可复用思路：用 RAW 的线性光响应与事件亮度变化构造物理约束做双模态去噪，以及基于去噪结果动态估计两模态 SNR 来引导自适应特征融合并注入扩散采样过程。
原文依据 dynamically estimating the SNR of both modalities based on denoising results to guide adaptive feature fusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论极端低光条件下对动态场景进行高质量成像极具挑战性。光子稀缺会引入严重噪声与纹理损失，导致图像显著退化。事件相机具有 120 dB 的高动态范围和对运动的高敏感性，能够为保留细微纹理提供关键线索，因而成为传统相机的有力补充。然而，现有方法大多强调从事件中恢复纹理，却很少关注图像噪声或事件自身的固有噪声，这最终阻碍了在光子匮乏条件下实现精确的像素重建。在本工作中，我们提出 NEC-Diff，一种新颖的基于扩散的事件-RAW 混合成像框架，能够从强噪声信号中提取可靠信息以重建精细的场景结构。该框架由两个关键洞见驱动：(1) 将 RAW 图像的线性光响应特性与事件的亮度变化本质相结合，建立物理驱动的约束，以实现鲁棒的双模态去噪；(2) 基于去噪结果动态估计两种模态的信噪比，以引导自适应特征融合，从而将可靠线索注入扩散过程，实现高保真视觉重建。此外，我们构建了 REAL（Raw and Event Acquired in Low-light）数据集，提供 47,800 张像素对齐的低光 RAW 图像、事件以及 0.001–0.8 lux 光照下的高质量参考图像。大量实验表明 NEC-Diff 在极端黑暗中具有优越性。
英文原文摘要 1573 字符
High-quality imaging of dynamic scenes in extremely low-light conditions is highly challenging. Photon scarcity induces severe noise and texture loss, causing significant image degradation. Event cameras, featuring a high dynamic range (120 dB) and high sensitivity to motion, serve as powerful complements to conventional cameras by offering crucial cues for preserving subtle textures. However, most existing approaches emphasize texture recovery from events, while paying little attention to image noise or the intrinsic noise of events themselves, which ultimately hinders accurate pixel reconstruction under photon-starved conditions. In this work, we propose NEC-Diff, a novel diffusion-based event-RAW hybrid imaging framework that extracts reliable information from heavily noisy signals to reconstruct fine scene structures. The framework is driven by two key insights: (1) combining the linear light-response property of RAW images with the brightness-change nature of events to establish a physics-driven constraint for robust dual-modal denoising; and (2) dynamically estimating the SNR of both modalities based on denoising results to guide adaptive feature fusion, thereby injecting reliable cues into the diffusion process for high-fidelity visual reconstruction. Furthermore, we construct the REAL (Raw and Event Acquired in Low-light) dataset which provides 47,800 pixel-aligned low-light RAW images, events, and high-quality references under 0.001-0.8 lux illumination. Extensive experiments demonstrate the superiority of NEC-Diff under extreme darkness.