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

• URL: http://arxiv.org/abs/2605.30939v1
• Date: Fri, 29 May 2026 07:28:08 GMT
• Title: IAF-Net: Illumination-Adaptive Fusion for Low-Light Urban Road Segmentation
• Abstract summary: We propose an end-to-end framework with illumination-adaptive fusion for robust road segmentation across different lighting conditions.<n>IAF-Net dynamically adjusts fusion weights of RGB and geometric features via the core Illumination-Adaptive Fusion (IAF) module.<n>Experiments on nuScenes-NRS show state-of-the-art overall performance among compared methods, while CARLA-MWRS further validates robustness across adverse weather conditions.
• Score: 6.81209407358202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement [48.364582443938296]
  Low-light image enhancement (LLIE) seeks to restore structural fidelity, natural color rendition, and proper exposure from images captured under inadequate lighting conditions.<n>Recent state-of-the-art approaches, such as CIDNet, adopt a dual-branch architecture comprising a chrominance (HV) branch and an intensity (I) branch to separately model decoupled and luminance information within the HVI color space.<n>These methods overlook the mutual interaction between intensity and chrominance components, which inherently limits their representational capacity and leads to suboptimal enhancement performance.
  arXiv  Detail & Related papers  (2026-08-03T08:27:38Z)
• Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation [0.6187780920448871]
  We propose a multi-modal fusion architecture built upon dual ConvNeXt V2 backbones that employs stage-wise, modality-adaptive fusion strategies.<n>Experiments on MFNet and PST900 demonstrate that our lightest variant achieves 61.73% and 86.24% mIoU, respectively, with only 35.43M parameters.
  arXiv  Detail & Related papers  (2026-05-25T18:57:22Z)
• AdaFuse-Det: Adaptive Cross-Modal Fusion of Event Cameras for Robust Object Detection in Low-Light RGB Imagery [2.804640719143954]
  We present AdaFuse-Det, a dual-stream framework that fuses CLAHE-enhanced RGB frames with voxelized event tensors.<n>On the LLE-VOS benchmark, AdaFuse-Det achieves a Recall of $65.54%$, Precision of $53.85%$, and F1-Score of $59.12%$ under severe illumination degradation.
  arXiv  Detail & Related papers  (2026-05-23T18:01:48Z)
• Seeing Roads Through Words: A Language-Guided Framework for RGB-T Driving Scene Segmentation [5.030754278104693]
  RGB-Thermal fusion is a standard approach, yet existing methods apply static fusion strategies uniformly across all conditions.<n>We propose CLARITY that dynamically adapts its fusion strategy to the detected scene condition.<n> Experiments on the MFNet dataset demonstrate that CLARITY establishes a new state-of-the-art (SOTA)
  arXiv  Detail & Related papers  (2026-02-07T03:52:04Z)
• SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement [58.79901582809091]
  Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>We present a Spatially-Adaptive Illumination-Guided Transformer framework that enables accurate illumination restoration.
  arXiv  Detail & Related papers  (2025-07-21T11:38:56Z)
• Towards Generalized Range-View LiDAR Segmentation in Adverse Weather [65.22588361803942]
  We identify and analyze the unique challenges that affect the generalization of range-view LiDAR segmentation in severe weather.<n>We propose a modular and lightweight framework that enhances robustness without altering the core architecture of existing models.<n>Our approach significantly improves generalization to adverse weather with minimal inference overhead.
  arXiv  Detail & Related papers  (2025-06-10T16:48:27Z)
• A Multi-modal Fusion Network for Terrain Perception Based on Illumination Aware [4.964908292792731]
  Road terrains play a crucial role in ensuring the driving safety of autonomous vehicles (AVs)<n>Existing sensors of AVs, including cameras and Lidars, are susceptible to variations in lighting and weather conditions.<n>We propose an illumination-aware multi-modal fusion network (IMF), which leverages both exteroceptive and proprioceptive perception.
  arXiv  Detail & Related papers  (2025-05-16T10:02:22Z)
• PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection [28.06976064484559]
  PedDet is an adaptive spectral optimization framework specifically enhanced and optimized for multispectral pedestrian detection.<n>PedDet achieves state-of-the-art performance, improving the mAP by 6.6% with superior detection accuracy even in low-light conditions.
  arXiv  Detail & Related papers  (2025-02-19T19:31:51Z)
• Multi-Modality Driven LoRA for Adverse Condition Depth Estimation [61.525312117638116]
  We propose Multi-Modality Driven LoRA (MMD-LoRA) for Adverse Condition Depth Estimation.<n>It consists of two core components: Prompt Driven Domain Alignment (PDDA) and Visual-Text Consistent Contrastive Learning (VTCCL)<n>It achieves state-of-the-art performance on the nuScenes and Oxford RobotCar datasets.
  arXiv  Detail & Related papers  (2024-12-28T14:23:58Z)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Searching a Compact Architecture for Robust Multi-Exposure Image Fusion [55.37210629454589]
  Two major stumbling blocks hinder the development, including pixel misalignment and inefficient inference. This study introduces an architecture search-based paradigm incorporating self-alignment and detail repletion modules for robust multi-exposure image fusion. The proposed method outperforms various competitive schemes, achieving a noteworthy 3.19% improvement in PSNR for general scenarios and an impressive 23.5% enhancement in misaligned scenarios.
  arXiv  Detail & Related papers  (2023-05-20T17:01:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.