# Towards Fast and Light-Weight Restoration of Dark Images

arXiv: https://arxiv.org/abs/2011.14133 · HTML: https://mlsanity.com/paper/2011.14133/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2020.

## Built on by (most cited first, 24 of 24)

- [Low-Light Image Enhancement via Structure Modeling and Guidance](https://mlsanity.com/paper/2305.05839/) (2023)
- [Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision](https://mlsanity.com/paper/2112.04719/) (2021)
- [GenISP: Neural ISP for Low-Light Machine Cognition](https://mlsanity.com/paper/2205.03688/) (2022)
- [Learning to See in the Extremely Dark](https://mlsanity.com/paper/2506.21132/) (2025)
- [Learning to See Low-Light Images via Feature Domain Adaptation](https://mlsanity.com/paper/2312.06723/) (2023)
- [Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance](https://mlsanity.com/paper/2312.15855/) (2023)
- [Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement](https://mlsanity.com/paper/2409.07040/) (2024)
- [Linear Array Network for Low-light Image Enhancement](https://mlsanity.com/paper/2201.08996/) (2022)
- [Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification](https://mlsanity.com/paper/2312.07338/) (2023)
- [Unsupervised network for low-light enhancement](https://mlsanity.com/paper/2306.02883/) (2023)
- [Bilevel Generative Learning for Low-Light Vision](https://mlsanity.com/paper/2308.03381/) (2023)
- [LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset](https://mlsanity.com/paper/2503.19804/) (2025)
- [Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition](https://mlsanity.com/paper/2106.04392/) (2021)
- [Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter](https://mlsanity.com/paper/2309.09443/) (2023)
- [GMTR: Graph Matching Transformers](https://mlsanity.com/paper/2311.08141/) (2023)
- [DarkShot: Lighting Dark Images with Low-Compute and High-Quality](https://mlsanity.com/paper/2312.16805/) (2023)
- [TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing](https://mlsanity.com/paper/2401.05431/) (2024)
- [TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks](https://mlsanity.com/paper/2401.05432/) (2024)
- [T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image](https://mlsanity.com/paper/2403.13663/) (2024)
- [Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms](https://mlsanity.com/paper/2408.17101/) (2024)
- [Towards General Deepfake Detection with Dynamic Curriculum](https://mlsanity.com/paper/2410.11162/) (2024)
- [Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/2410.13409/) (2024)
- [Mask6D: Masked Pose Priors For 6D Object Pose Estimation](https://mlsanity.com/paper/2507.06486/) (2025)
- [When Extreme Darkness Meets Motion Blur: MeanFlow for Unified RAW Restoration](https://mlsanity.com/paper/2608.01720/) (2026)

## Abstract (arXiv)

The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and processing power. With this in mind, we propose a deep neural network architecture that aims to strike a balance between the network latency, memory utilization, model parameters, and reconstruction quality. The key idea is to forbid computations in the High-Resolution (HR) space and limit them to a Low-Resolution (LR) space. However, doing the bulk of computations in the LR space causes artifacts in the restored image. We thus propose Pack and UnPack operations, which allow us to effectively transit between the HR and LR spaces without incurring much artifacts in the restored image. We show that we can enhance a full resolution, 2848 x 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 - 7x fewer model parameters, 2 - 3x lower memory utilization, 5 - 20x speed up and yet maintain a competitive image reconstruction quality compared to the state-of-the-art algorithms.