# IAF-Net: Illumination-Adaptive Fusion for Low-Light Urban Road Segmentation

arXiv: https://arxiv.org/abs/2605.30939 · HTML: https://mlsanity.com/paper/2605.30939/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 29 of 29)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images](https://mlsanity.com/paper/2003.04645/) (2020)
- [Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2205.00858/) (2022)
- [Progressive LiDAR Adaptation for Road Detection](https://mlsanity.com/paper/1904.01206/) (2019)
- [ORFD: A Dataset and Benchmark for Off-Road Freespace Detection](https://mlsanity.com/paper/2206.09907/) (2022)
- [CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes](https://mlsanity.com/paper/2410.10791/) (2024)
- [CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation](https://mlsanity.com/paper/2307.15942/) (2023)
- [RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing](https://mlsanity.com/paper/2309.10356/) (2023)
- [Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs](https://mlsanity.com/paper/2007.05950/) (2020)
- [Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement](https://mlsanity.com/paper/2307.09362/) (2023)
- [RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion](https://mlsanity.com/paper/2407.21631/) (2024)
- [Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey](https://mlsanity.com/paper/2401.07801/) (2024)
- [SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection](https://mlsanity.com/paper/2402.18918/) (2024)
- [ROD: RGB-Only Fast and Efficient Off-road Freespace Detection](https://mlsanity.com/paper/2508.08697/) (2025)
- [Annotation-Free Detection of Drivable Areas and Curbs Leveraging LiDAR Point Cloud Maps](https://mlsanity.com/paper/2603.27553/) (2026)
- [LiteViLNet: Lightweight Vision-LiDAR Fusion Network for Efficient Road Segmentation](https://mlsanity.com/paper/2605.21007/) (2026)

## Abstract (arXiv)

Semantic road segmentation is important for autonomous driving, but existing methods suffer severe performance degradation under low-light conditions. Many existing multi-modal fusion methods do not explicitly adapt to illumination-dependent changes in modality reliability, which can propagate degraded RGB features into the fused representation at night. We propose IAF-Net (Illumination-Adaptive Fusion Network), an end-to-end framework with illumination-adaptive fusion for robust road segmentation across different lighting conditions. It dynamically adjusts fusion weights of RGB and geometric features via the core Illumination-Adaptive Fusion (IAF) module, and enhances low-light feature selection with a brightness-modulated attention decoder. We also construct two dedicated datasets: nuScenes Nighttime Road Segmentation (nuScenes-NRS) and CARLA Multi-Weather Road Segmentation (CARLA-MWRS). Experiments on nuScenes-NRS show state-of-the-art overall performance among the compared methods, while CARLA-MWRS further validates robustness across adverse weather conditions. Ablation studies on a 40% training subset further highlight the importance of the IAF module, which provides the largest individual gain of 0.70% in MaxF.