# NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness

arXiv: https://arxiv.org/abs/2603.20005 · HTML: https://mlsanity.com/paper/2603.20005/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [Events-to-Video: Bringing Modern Computer Vision to Event Cameras](https://mlsanity.com/paper/1904.08298/) (2019)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy](https://mlsanity.com/paper/2009.08283/) (2020)
- [Iterative Prompt Learning for Unsupervised Backlit Image Enhancement](https://mlsanity.com/paper/2303.17569/) (2023)
- [Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1811.08230/) (2018)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models](https://mlsanity.com/paper/2407.08939/) (2024)
- [Rethinking Noise Synthesis and Modeling in Raw Denoising](https://mlsanity.com/paper/2110.04756/) (2021)
- [Zero-Reference Low-Light Enhancement via Physical Quadruple Priors](https://mlsanity.com/paper/2403.12933/) (2024)
- [Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach](https://mlsanity.com/paper/2404.00834/) (2024)
- [Abandoning the Bayer-Filter to See in the Dark](https://mlsanity.com/paper/2203.04042/) (2022)
- [Seeing Motion at Nighttime with an Event Camera](https://mlsanity.com/paper/2404.11884/) (2024)
- [Low-Light Video Enhancement with Synthetic Event Guidance](https://mlsanity.com/paper/2208.11014/) (2022)
- [Towards Low Light Enhancement with RAW Images](https://mlsanity.com/paper/2112.14022/) (2021)
- [Towards Real-world Event-guided Low-light Video Enhancement and Deblurring](https://mlsanity.com/paper/2408.14916/) (2024)
- [EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset](https://mlsanity.com/paper/2312.08220/) (2023)
- [Binarized Low-light Raw Video Enhancement](https://mlsanity.com/paper/2403.19944/) (2024)
- [Unraveling the paradox of intensity-dependent DVS pixel noise](https://mlsanity.com/paper/2109.08640/) (2021)
- [EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More](https://mlsanity.com/paper/2408.16254/) (2024)
- [Low-Light Image Enhancement using Event-Based Illumination Estimation](https://mlsanity.com/paper/2504.09379/) (2025)
- [Learning to See in the Extremely Dark](https://mlsanity.com/paper/2506.21132/) (2025)
- [Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising](https://mlsanity.com/paper/2505.00045/) (2025)
- [Noise2Image: Noise-Enabled Static Scene Recovery for Event Cameras](https://mlsanity.com/paper/2404.01298/) (2024)
- [ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement](https://mlsanity.com/paper/2503.02484/) (2025)
- [Exploring Fourier Prior and Event Collaboration for Low-Light Image Enhancement](https://mlsanity.com/paper/2508.00308/) (2025)

## Abstract (arXiv)

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. The project are available at: https://github.com/jinghan-xu/NEC-Diff.