# Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition

arXiv: https://arxiv.org/abs/2405.15660 · HTML: https://mlsanity.com/paper/2405.15660/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Low-Light Image Enhancement via Structure Modeling and Guidance](https://mlsanity.com/paper/2305.05839/) (2023)
- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [Zero-Reference Low-Light Enhancement via Physical Quadruple Priors](https://mlsanity.com/paper/2403.12933/) (2024)
- [Lighting up NeRF via Unsupervised Decomposition and Enhancement](https://mlsanity.com/paper/2307.10664/) (2023)
- [Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression](https://mlsanity.com/paper/1512.02311/) (2015)
- [Low-Light Video Enhancement with Synthetic Event Guidance](https://mlsanity.com/paper/2208.11014/) (2022)
- [PMatch: Paired Masked Image Modeling for Dense Geometric Matching](https://mlsanity.com/paper/2303.17342/) (2023)
- [Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping](https://mlsanity.com/paper/2007.09187/) (2020)
- [Binarized Low-light Raw Video Enhancement](https://mlsanity.com/paper/2403.19944/) (2024)
- [Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution](https://mlsanity.com/paper/2207.01797/) (2022)
- [Low Light Video Enhancement by Learning on Static Videos with Cross-Frame Attention](https://mlsanity.com/paper/2210.04290/) (2022)

## Built on by (most cited first, 6 of 6)

- [Learning Latent Proxies for Controllable Single-Image Relighting](https://mlsanity.com/paper/2603.15555/) (2026)
- [PixIE: Prompted Pixel-Space Low-Light Image Enhancement](https://mlsanity.com/paper/2605.23531/) (2026)
- [Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement](https://mlsanity.com/paper/2510.17105/) (2025)
- [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)
- [OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation](https://mlsanity.com/paper/2610.20501/) (2026)

## Abstract (arXiv)

Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition strategy that incorporates view-independent and view-dependent components to enhance the performance of LLVE. We leverage dynamic cross-frame correspondences for the view-independent term (which primarily captures intrinsic appearance) and impose a scene-level continuity constraint on the view-dependent term (which mainly describes the shading condition) to achieve consistent and satisfactory decomposition results. To further ensure consistent decomposition, we introduce a dual-structure enhancement network featuring a cross-frame interaction mechanism. By supervising different frames simultaneously, this network encourages them to exhibit matching decomposition features. This mechanism can seamlessly integrate with encoder-decoder single-frame networks, incurring minimal additional parameter costs. Extensive experiments are conducted on widely recognized LLVE benchmarks, covering diverse scenarios. Our framework consistently outperforms existing methods, establishing a new SOTA performance.