# Multi-Scale Denoising in the Feature Space for Low-Light Instance Segmentation

arXiv: https://arxiv.org/abs/2402.18307 · HTML: https://mlsanity.com/paper/2402.18307/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset](https://mlsanity.com/paper/1908.00682/) (2019)
- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [Night-time Scene Parsing with a Large Real Dataset](https://mlsanity.com/paper/2003.06883/) (2020)
- [A Comprehensive Study of Object Tracking in Low-Light Environments](https://mlsanity.com/paper/2312.16250/) (2023)

## Built on by (most cited first, 4 of 4)

- [Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline](https://mlsanity.com/paper/2504.12169/) (2025)
- [ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark](https://mlsanity.com/paper/2512.01495/) (2025)
- [PixIE: Prompted Pixel-Space Low-Light Image Enhancement](https://mlsanity.com/paper/2605.23531/) (2026)
- [OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation](https://mlsanity.com/paper/2610.20501/) (2026)

## Abstract (arXiv)

Instance segmentation for low-light imagery remains largely unexplored due to the challenges imposed by such conditions, for example shot noise due to low photon count, color distortions and reduced contrast. In this paper, we propose an end-to-end solution to address this challenging task. Our proposed method implements weighted non-local blocks (wNLB) in the feature extractor. This integration enables an inherent denoising process at the feature level. As a result, our method eliminates the need for aligned ground truth images during training, thus supporting training on real-world low-light datasets. We introduce additional learnable weights at each layer in order to enhance the network's adaptability to real-world noise characteristics, which affect different feature scales in different ways. Experimental results on several object detectors show that the proposed method outperforms the pretrained networks with an Average Precision (AP) improvement of at least +7.6, with the introduction of wNLB further enhancing AP by upto +1.3.