# Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm

arXiv: https://arxiv.org/abs/2602.08699 · HTML: https://mlsanity.com/paper/2602.08699/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 73 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 30 of 46)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond](https://mlsanity.com/paper/2012.02181/) (2020)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [YouTube-VOS: Sequence-to-Sequence Video Object Segmentation](https://mlsanity.com/paper/1809.00461/) (2018)
- [TDAN: Temporally Deformable Alignment Network for Video Super-Resolution](https://mlsanity.com/paper/1812.02898/) (2018)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Low-Light Image Enhancement with Wavelet-based Diffusion Models](https://mlsanity.com/paper/2306.00306/) (2023)
- [Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution](https://mlsanity.com/paper/2002.11616/) (2020)
- [Video Super-resolution with Temporal Group Attention](https://mlsanity.com/paper/2007.10595/) (2020)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [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)

## 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. The framework is called View-aware Low-light Video Enhancement (VLLVE). 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. Building upon VLLVE, we propose a more comprehensive decomposition strategy by introducing an additive residual term, resulting in VLLVE++. This residual term can simulate scene-adaptive degradations, which are difficult to model using a decomposition formulation for common scenes, thereby further enhancing the ability to capture the overall content of videos. In addition, VLLVE++ enables bidirectional learning for both enhancement and degradation-aware correspondence refinement (end-to-end manner), effectively increasing reliable correspondences while filtering out incorrect ones. Notably, VLLVE++ demonstrates strong capability in handling challenging cases, such as real-world scenes and videos with high dynamics. Extensive experiments are conducted on widely recognized LLVE benchmarks.