# DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior

arXiv: https://arxiv.org/abs/2303.06834 · HTML: https://mlsanity.com/paper/2303.06834/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Learning to predict crisp boundaries](https://mlsanity.com/paper/1807.10097/) (2018)
- [Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion](https://mlsanity.com/paper/1910.04066/) (2019)
- [NBNet: Noise Basis Learning for Image Denoising with Subspace Projection](https://mlsanity.com/paper/2012.15028/) (2020)
- [Practical Deep Raw Image Denoising on Mobile Devices](https://mlsanity.com/paper/2010.06935/) (2020)
- [Deformable Kernel Networks for Joint Image Filtering](https://mlsanity.com/paper/1910.08373/) (2019)
- [Joint Image Filtering with Deep Convolutional Networks](https://mlsanity.com/paper/1710.04200/) (2017)
- [Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser](https://mlsanity.com/paper/2103.10234/) (2021)
- [An Integrated Enhancement Solution for 24-hour Colorful Imaging](https://mlsanity.com/paper/2005.04580/) (2020)

## Built on by (most cited first, 19 of 19)

- [Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Dark](https://mlsanity.com/paper/2303.11642/) (2023)
- [Pixel-aligned RGB-NIR Stereo Imaging and Dataset for Robot Vision](https://mlsanity.com/paper/2411.18025/) (2024)
- [Boosting Image Restoration via Priors from Pre-trained Models](https://mlsanity.com/paper/2403.06793/) (2024)
- [VIFNet: An End-to-end Visible-Infrared Fusion Network for Image Dehazing](https://mlsanity.com/paper/2404.07790/) (2024)
- [Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising](https://mlsanity.com/paper/2412.16645/) (2024)
- [NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset](https://mlsanity.com/paper/2404.08514/) (2024)
- [SGDFormer: One-stage Transformer-based Architecture for Cross-Spectral Stereo Image Guided Denoising](https://mlsanity.com/paper/2404.00349/) (2024)
- [Towards RGB-NIR Cross-modality Image Registration and Beyond](https://mlsanity.com/paper/2405.19914/) (2024)
- [Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark](https://mlsanity.com/paper/2607.29684/) (2026)
- [ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions](https://mlsanity.com/paper/2409.05327/) (2024)
- [Near-infrared Image Deblurring and Event Denoising with Synergistic Neuromorphic Imaging](https://mlsanity.com/paper/2503.01193/) (2025)
- [Bi-directional Self-Registration for Misaligned Infrared-Visible Image Fusion](https://mlsanity.com/paper/2505.06920/) (2025)
- [RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection](https://mlsanity.com/paper/2306.12621/) (2023)
- [Visible and NIR Image Fusion Algorithm Based on Information Complementarity](https://mlsanity.com/paper/2309.10522/) (2023)
- [No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency](https://mlsanity.com/paper/2602.23559/) (2026)
- [Preliminary analysis of RGB-NIR Image Registration techniques for off-road forestry environments](https://mlsanity.com/paper/2603.11952/) (2026)
- [Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising](https://mlsanity.com/paper/2604.16800/) (2026)
- [Dual-Integrated Low-Latency Single-Lens Infrared Computational Imaging for Object Detection](https://mlsanity.com/paper/2605.21964/) (2026)
- [Geometry-aware Depth-guided Representation Learning for Structure-preserving Low-light Image Enhancement](https://mlsanity.com/paper/2607.05005/) (2026)

## Abstract (arXiv)

RGB-NIR fusion is a promising method for low-light imaging. However, high-intensity noise in low-light images amplifies the effect of structure inconsistency between RGB-NIR images, which fails existing algorithms. To handle this, we propose a new RGB-NIR fusion algorithm called Dark Vision Net (DVN) with two technical novelties: Deep Structure and Deep Inconsistency Prior (DIP). The Deep Structure extracts clear structure details in deep multiscale feature space rather than raw input space, which is more robust to noisy inputs. Based on the deep structures from both RGB and NIR domains, we introduce the DIP to leverage the structure inconsistency to guide the fusion of RGB-NIR. Benefiting from this, the proposed DVN obtains high-quality lowlight images without the visual artifacts. We also propose a new dataset called Dark Vision Dataset (DVD), consisting of aligned RGB-NIR image pairs, as the first public RGBNIR fusion benchmark. Quantitative and qualitative results on the proposed benchmark show that DVN significantly outperforms other comparison algorithms in PSNR and SSIM, especially in extremely low light conditions.