# Low Light Video Enhancement by Learning on Static Videos with Cross-Frame Attention

arXiv: https://arxiv.org/abs/2210.04290 · HTML: https://mlsanity.com/paper/2210.04290/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Video Object Segmentation with Language Referring Expressions](https://mlsanity.com/paper/1803.08006/) (2018)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Video Super-Resolution Transformer](https://mlsanity.com/paper/2106.06847/) (2021)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping](https://mlsanity.com/paper/2007.09187/) (2020)
- [Single-frame Regularization for Temporally Stable CNNs](https://mlsanity.com/paper/1902.10424/) (2019)
- [Revealing Disocclusions in Temporal View Synthesis through Infilling Vector Prediction](https://mlsanity.com/paper/2110.08805/) (2021)

## Built on by (most cited first, 5 of 5)

- [Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition](https://mlsanity.com/paper/2405.15660/) (2024)
- [RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image Enhancement](https://mlsanity.com/paper/2409.04363/) (2024)
- [Optimizing 4D Lookup Table for Low-light Video Enhancement via Wavelet Priori](https://mlsanity.com/paper/2409.08585/) (2024)
- [Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm](https://mlsanity.com/paper/2602.08699/) (2026)
- [AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference](https://mlsanity.com/paper/2606.11186/) (2026)

## Abstract (arXiv)

The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or moving cameras where a long exposure ground truth cannot be captured. We approach this problem by training a model on static videos such that the model can generalize to dynamic videos. Existing methods adopting this approach operate frame by frame and do not exploit the relationships among neighbouring frames. We overcome this limitation through a selfcross dilated attention module that can effectively learn to use information from neighbouring frames even when dynamics between the frames are different during training and test times. We validate our approach through experiments on multiple datasets and show that our method outperforms other state-of-the-art video enhancement algorithms when trained only on static videos.