# Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement

arXiv: https://arxiv.org/abs/2503.11175 · HTML: https://mlsanity.com/paper/2503.11175/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Artificial Intelligence in the Creative Industries: A Review](https://mlsanity.com/paper/2007.12391/) (2020)
- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement](https://mlsanity.com/paper/2110.00970/) (2021)
- [Revisiting Temporal Alignment for Video Restoration](https://mlsanity.com/paper/2111.15288/) (2021)
- [Contextual colorization and denoising for low-light ultra high resolution sequences](https://mlsanity.com/paper/2101.01597/) (2021)
- [A Spatio-temporal Aligned SUNet Model for Low-light Video Enhancement](https://mlsanity.com/paper/2403.02408/) (2024)
- [BVI-RLV: A Fully Registered Dataset for Low-Light Video Enhancement](https://mlsanity.com/paper/2407.03535/) (2024)
- [AquaNeRF: Neural Radiance Fields in Underwater Media with Distractor Removal](https://mlsanity.com/paper/2502.16351/) (2025)
- [Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement](https://mlsanity.com/paper/2408.12316/) (2024)

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

- [RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction](https://mlsanity.com/paper/2505.15737/) (2025)
- [BVI-Mamba: Video Enhancement Using a Visual State-Space Model for Low-Light and Underwater Environments](https://mlsanity.com/paper/2604.23655/) (2026)
- [Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques](https://mlsanity.com/paper/2507.08375/) (2025)
- [AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference](https://mlsanity.com/paper/2606.11186/) (2026)
- [OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation](https://mlsanity.com/paper/2610.20501/) (2026)

## Abstract (arXiv)

Low-light and underwater videos suffer from poor visibility, low contrast, and high noise, necessitating enhancements in visual quality. However, existing approaches typically rely on paired ground truth, which limits their practicality and often fails to maintain temporal consistency. To overcome these obstacles, this paper introduces a novel zero-shot learning approach named Zero-TIG, leveraging the Retinex theory and optical flow techniques. The proposed network consists of an enhancement module and a temporal feedback module. The enhancement module comprises three subnetworks: low-light image denoising, illumination estimation, and reflection denoising. The temporal enhancement module ensures temporal consistency by incorporating histogram equalization, optical flow computation, and image warping to align the enhanced previous frame with the current frame, thereby maintaining continuity. Additionally, we address color distortion in underwater data by adaptively balancing RGB channels. The experimental results demonstrate that our method achieves low-light video enhancement without the need for paired training data, making it a promising and applicable method for real-world scenario enhancement.