# See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion

arXiv: https://arxiv.org/abs/1908.05868 · HTML: https://mlsanity.com/paper/1908.05868/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 30 of 30)

- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2205.00858/) (2022)
- [Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.11062/) (2021)
- [Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions](https://mlsanity.com/paper/2207.06825/) (2022)
- [Day-to-Night Image Synthesis for Training Nighttime Neural ISPs](https://mlsanity.com/paper/2206.02715/) (2022)
- [NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night](https://mlsanity.com/paper/2204.05538/) (2022)
- [Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters](https://mlsanity.com/paper/2207.01331/) (2022)
- [Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement](https://mlsanity.com/paper/2307.09362/) (2023)
- [GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data](https://mlsanity.com/paper/2207.13297/) (2022)
- [Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning](https://mlsanity.com/paper/2203.10395/) (2022)
- [ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentation](https://mlsanity.com/paper/2402.06446/) (2024)
- [Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos](https://mlsanity.com/paper/2105.07209/) (2021)
- [LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation](https://mlsanity.com/paper/2211.11870/) (2022)
- [Improving Road Segmentation in Challenging Domains Using Similar Place Priors](https://mlsanity.com/paper/2205.14112/) (2022)
- [Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning](https://mlsanity.com/paper/2309.16351/) (2023)
- [Using simulation to quantify the performance of automotive perception systems](https://mlsanity.com/paper/2303.00983/) (2023)
- [Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation](https://mlsanity.com/paper/2310.04747/) (2023)
- [Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning](https://mlsanity.com/paper/2310.15688/) (2023)
- [RHRSegNet: Relighting High-Resolution Night-Time Semantic Segmentation](https://mlsanity.com/paper/2407.06016/) (2024)
- [Multi-modal Visual Place Recognition in Dynamics-Invariant Perception Space](https://mlsanity.com/paper/2105.07800/) (2021)
- [Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint](https://mlsanity.com/paper/2106.16000/) (2021)
- [DGSS : Domain Generalized Semantic Segmentation using Iterative Style Mining and Latent Representation Alignment](https://mlsanity.com/paper/2202.13144/) (2022)
- [Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight](https://mlsanity.com/paper/2212.02053/) (2022)
- [ISETHDR: A Physics-based Synthetic Radiance Dataset for High Dynamic Range Driving Scenes](https://mlsanity.com/paper/2408.12048/) (2024)
- [Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks](https://mlsanity.com/paper/2204.01795/) (2022)
- [Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving Scenes](https://mlsanity.com/paper/2306.13725/) (2023)
- [Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss](https://mlsanity.com/paper/2310.08206/) (2023)
- [Towards Closing the Domain Gap with Event Cameras](https://mlsanity.com/paper/2512.16178/) (2025)
- [Prototype Learning-Based Few-Shot Segmentation for Low-Light Crack on Concrete Structures](https://mlsanity.com/paper/2601.13059/) (2026)

## Abstract (arXiv)

Currently, semantic segmentation shows remarkable efficiency and reliability in standard scenarios such as daytime scenes with favorable illumination conditions. However, in face of adverse conditions such as the nighttime, semantic segmentation loses its accuracy significantly. One of the main causes of the problem is the lack of sufficient annotated segmentation datasets of nighttime scenes. In this paper, we propose a framework to alleviate the accuracy decline when semantic segmentation is taken to adverse conditions by using Generative Adversarial Networks (GANs). To bridge the daytime and nighttime image domains, we made key observation that compared to datasets in adverse conditions, there are considerable amount of segmentation datasets in standard conditions such as BDD and our collected ZJU datasets. Our GAN-based nighttime semantic segmentation framework includes two methods. In the first method, GANs were used to translate nighttime images to the daytime, thus semantic segmentation can be performed using robust models already trained on daytime datasets. In another method, we use GANs to translate different ratio of daytime images in the dataset to the nighttime but still with their labels. In this sense, synthetic nighttime segmentation datasets can be generated to yield models prepared to operate at nighttime conditions robustly. In our experiment, the later method significantly boosts the performance at the nighttime evidenced by quantitative results using Intersection over Union (IoU) and Pixel Accuracy (Acc). We show that the performance varies with respect to the proportion of synthetic nighttime images in the dataset, where the sweet spot corresponds to most robust performance across the day and night.