A Spatio-temporal Aligned SUNet Model for Low-light Video Enhancement
Abstract: Distortions caused by low-light conditions are not only visually unpleasant but also degrade the performance of computer vision tasks. The restoration and enhancement have proven to be highly beneficial. However, there are only a limited number of enhancement methods explicitly designed for videos acquired in low-light conditions. We propose a Spatio-Temporal Aligned SUNet (STA-SUNet) model using a Swin Transformer as a backbone to capture low light video features and exploit their spatio-temporal correlations. The STA-SUNet model is trained on a novel, fully registered dataset (BVI), which comprises dynamic scenes captured under varying light conditions. It is further analysed comparatively against various other models over three test datasets. The model demonstrates superior adaptivity across all datasets, obtaining the highest PSNR and SSIM values. It is particularly effective in extreme low-light conditions, yielding fairly good visualisation results.
- “A Comprehensive Study of Object Tracking in Low-Light Environments,” arXiv:2312.16250, 2023.
- “SNR-Aware Low-Light Image Enhancement,” IEEE/CVF CVPR, pp. 17714–17724, 2022.
- “Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement,” IEEE/CVF ICCV, pp. 4419–4428, 2021.
- “Toward Fast, Flexible, and Robust Low-Light Image Enhancement,” arXiv:2204.10137, 2022.
- “Contextual Colorization and Denoising for Low-Light Ultra High Resolution Sequences,” IEEE/CVF ICIP proc., pp. 1614–1618, 2021.
- “Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping,” arXiv:2007.09187, 2020.
- “BVI-Lowlight: Fully Registered Datasets for Low-light Image and Video Enhancement,” arXiv:2402.01970, 2024.
- “Attention Is All You Need,” arXiv:1706.03762, 2023.
- “SUNet: Swin Transformer UNet for Image Denoising,” arXiv:2202.14009, 2022.
- “EDVR: Video Restoration with Enhanced Deformable Convolutional Networks,” arXiv:1905.02716, 2019.
- “Brightness Preserving Dynamic Histogram Equalization for Image Contrast Enhancement,” IEEE/CVF TCE, vol. 53, no. 4, pp. 1752–1758, 2007.
- “A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation,” IEEE/CVF TIP, vol. 24, no. 12, pp. 4965–4977, 2015.
- Guang Deng, “A Generalized Unsharp Masking Algorithm,” IEEE/CVF TIP, vol. 20, no. 5, pp. 1249–1261, 2011.
- “Nonlocal transform-domain filter for volumetric data denoising and reconstruction,” IEEE TIP, vol. 22, no. 1, pp. 119–133, 2013.
- “LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement,” Pattern Recognition, vol. 61, pp. 650–662, 2017.
- “Low-Light Image and Video Enhancement Using Deep Learning: A Survey,” arXiv:2104.10729, 2021.
- “Deep Residual Learning for Image Recognition,” arXiv:1512.03385, 2015.
- “U-Net: Convolutional Networks for Biomedical Image Segmentation,” MICCAI, pp. 234–241, 2015.
- “Learning to See in the Dark,” arXiv:1805.01934, 2018.
- “Seeing Motion in the Dark,” IEEE/CVF ICCV, pp. 3184–3193, 2019.
- “Learning to See Moving Objects in the Dark,” IEEE/CVF ICCV, pp. 7323–7332, 2019.
- “Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset with Mechatronic Alignment,” IEEE/CVF ICCV, pp. 9680–9689, 2021.
- “Deformable convolutional networks,” arXiv:1703.06211, 2017.
- “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” arXiv:2103.14030, 2021.
- “Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network,” arXiv:1609.05158, 2016.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.