A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint

• URL: http://arxiv.org/abs/2403.18548v1
• Date: Wed, 27 Mar 2024 13:27:02 GMT
• Title: A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint
• Authors: Xiaofeng Cong, Jie Gui, Jing Zhang, Junming Hou, Hao Shen,
• Abstract summary: We propose a semi-supervised model for real-world nighttime dehazing. First, the spatial attention and frequency spectrum filtering are implemented as a spatial-frequency domain information interaction module. Second, a pseudo-label-based retraining strategy and a local window-based brightness loss for semi-supervised training process is designed to suppress haze and glow.
• Score: 19.723367790947684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing research based on deep learning has extensively explored the problem of daytime image dehazing. However, few studies have considered the characteristics of nighttime hazy scenes. There are two distinctions between nighttime and daytime haze. First, there may be multiple active colored light sources with lower illumination intensity in nighttime scenes, which may cause haze, glow and noise with localized, coupled and frequency inconsistent characteristics. Second, due to the domain discrepancy between simulated and real-world data, unrealistic brightness may occur when applying a dehazing model trained on simulated data to real-world data. To address the above two issues, we propose a semi-supervised model for real-world nighttime dehazing. First, the spatial attention and frequency spectrum filtering are implemented as a spatial-frequency domain information interaction module to handle the first issue. Second, a pseudo-label-based retraining strategy and a local window-based brightness loss for semi-supervised training process is designed to suppress haze and glow while achieving realistic brightness. Experiments on public benchmarks validate the effectiveness of the proposed method and its superiority over state-of-the-art methods. The source code and Supplementary Materials are placed in the https://github.com/Xiaofeng-life/SFSNiD.

Related papers

• Beyond Night Visibility: Adaptive Multi-Scale Fusion of Infrared and Visible Images [49.75771095302775]
  We propose an Adaptive Multi-scale Fusion network (AMFusion) with infrared and visible images. First, we separately fuse spatial and semantic features from infrared and visible images, where the former are used for the adjustment of light distribution. Second, we utilize detection features extracted by a pre-trained backbone that guide the fusion of semantic features. Third, we propose a new illumination loss to constrain fusion image with normal light intensity.
  arXiv  Detail & Related papers  (2024-03-02T03:52:07Z)
• Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation [33.142262765252795]
  Detectors trained on well-lit data exhibit significant performance degradation on low-light data due to low visibility. We propose to boost low-light object detection with zero-shot day-night domain adaptation. Our method generalizes a detector from well-lit scenarios to low-light ones without requiring real low-light data.
  arXiv  Detail & Related papers  (2023-12-02T20:11:48Z)
• Robust Monocular Depth Estimation under Challenging Conditions [81.57697198031975]
  State-of-the-art monocular depth estimation approaches are highly unreliable under challenging illumination and weather conditions. We tackle these safety-critical issues with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions.
  arXiv  Detail & Related papers  (2023-08-18T17:59:01Z)
• NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer [39.90066556289063]
  We propose an end-to-end transformer-based framework for nighttime haze removal, called NightHazeFormer. Our proposed approach consists of two stages: supervised pre-training and semi-supervised fine-tuning. Experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods.
  arXiv  Detail & Related papers  (2023-05-16T15:26:09Z)
• Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation [97.0195314255101]
  Inverse path tracing is expensive to compute, and ambiguities exist between reflection and emission. Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formulation. Our algorithm enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities.
  arXiv  Detail & Related papers  (2023-04-12T07:46:05Z)
• Boosting Night-time Scene Parsing with Learnable Frequency [53.05778451012621]
  Night-Time Scene Parsing (NTSP) is essential to many vision applications, especially for autonomous driving. Most of the existing methods are proposed for day-time scene parsing. We show that our method performs favorably against the state-of-the-art methods on the NightCity, NightCity+ and BDD100K-night datasets.
  arXiv  Detail & Related papers  (2022-08-30T13:09:59Z)
• Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark [20.66405067066299]
  We introduce Priors-Based Regularization to learn distribution knowledge from unpaired depth maps. We also leverage Mapping-Consistent Image Enhancement module to enhance image visibility and contrast. Our framework achieves remarkable improvements and state-of-the-art results on two nighttime datasets.
  arXiv  Detail & Related papers  (2021-08-09T06:24:35Z)
• Nighttime Dehazing with a Synthetic Benchmark [147.21955799938115]
  We propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images. We generate realistic nighttime hazy images by sampling real-world light colors from a prior empirical distribution. Experiment results demonstrate their superiority over state-of-the-art methods in terms of both image quality and runtime.
  arXiv  Detail & Related papers  (2020-08-10T02:16:46Z)
• Object-based Illumination Estimation with Rendering-aware Neural Networks [56.01734918693844]
  We present a scheme for fast environment light estimation from the RGBD appearance of individual objects and their local image areas. With the estimated lighting, virtual objects can be rendered in AR scenarios with shading that is consistent to the real scene.
  arXiv  Detail & Related papers  (2020-08-06T08:23:19Z)

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.