DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal

• URL: http://arxiv.org/abs/2508.02113v1
• Date: Mon, 04 Aug 2025 06:49:48 GMT
• Title: DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal
• Authors: Yihang Huang, Yuanfei Huang, Junhui Lin, Hua Huang,
• Abstract summary: We present DeflareMamba, a sequence model for lens flare removal.<n>We show that our method effectively removes various types of flare artifacts, including scattering and reflective flares.<n>Further downstream applications demonstrate the capacity of our method to improve visual object recognition and cross-modal semantic understanding.
• Score: 14.87987455441087
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Lens flare removal remains an information confusion challenge in the underlying image background and the optical flares, due to the complex optical interactions between light sources and camera lens. While recent solutions have shown promise in decoupling the flare corruption from image, they often fail to maintain contextual consistency, leading to incomplete and inconsistent flare removal. To eliminate this limitation, we propose DeflareMamba, which leverages the efficient sequence modeling capabilities of state space models while maintains the ability to capture local-global dependencies. Particularly, we design a hierarchical framework that establishes long-range pixel correlations through varied stride sampling patterns, and utilize local-enhanced state space models that simultaneously preserves local details. To the best of our knowledge, this is the first work that introduces state space models to the flare removal task. Extensive experiments demonstrate that our method effectively removes various types of flare artifacts, including scattering and reflective flares, while maintaining the natural appearance of non-flare regions. Further downstream applications demonstrate the capacity of our method to improve visual object recognition and cross-modal semantic understanding. Code is available at https://github.com/BNU-ERC-ITEA/DeflareMamba.

Related papers

• Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal [18.825840100537174]
  Lens flares arise from light reflection and refraction within sensor arrays, whose diverse types include glow, veiling glare, reflective flare and so on.<n>Existing methods are specialized for one specific type only, and overlook the simultaneous occurrence of multiple typed lens flares.<n>We introduce a solution named Self-supervised Generation-based Lens Flare Removal Network (SGLFR-Net), which is self-supervised without pre-training.
  arXiv  Detail & Related papers  (2025-02-15T08:04:38Z)
• ExpRDiff: Short-exposure Guided Diffusion Model for Realistic Local Motion Deblurring [61.82010103478833]
  We develop a context-based local blur detection module that incorporates additional contextual information to improve the identification of blurry regions.<n>Considering that modern smartphones are equipped with cameras capable of providing short-exposure images, we develop a blur-aware guided image restoration method.<n>We formulate the above components into a simple yet effective network, named ExpRDiff.
  arXiv  Detail & Related papers  (2024-12-12T11:42:39Z)
• GN-FR:Generalizable Neural Radiance Fields for Flare Removal [11.646119341279164]
  We propose a framework to render flare-free views from a sparse set of input images affected by lens flare.<n>We present a 3D multi-view flare dataset, comprising 17 real flare scenes with 782 images, 80 real flare patterns, and their corresponding annotated flare-occupancy masks.
  arXiv  Detail & Related papers  (2024-12-11T08:43:52Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models [55.99654128127689]
  Visual Foundation Models (VFMs) are used to generate semantic labels for weakly-supervised pixel-to-point contrastive distillation.<n>We adapt sampling probabilities of points to address imbalances in spatial distribution and category frequency.<n>Our approach consistently surpasses existing image-to-LiDAR contrastive distillation methods in downstream tasks.
  arXiv  Detail & Related papers  (2024-05-23T07:48:19Z)
• Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal [44.35766203309201]
  Intense light sources often produce flares in captured images at night, which deteriorates the visual quality and negatively affects downstream applications. In order to train an effective flare removal network, a reliable dataset is essential. We synthesize a prior-guided dataset named Flare7K*, which contains multi-flare images where the brightness of flares adheres to the laws of illumination. We propose a plug-and-play Adaptive Focus Module (AFM) that can adaptively mask the clean background areas and assist models in focusing on the regions severely affected by flares.
  arXiv  Detail & Related papers  (2024-03-30T10:37:56Z)
• Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery [69.71080926778413]
  flare artifacts can affect image visual quality and downstream computer vision tasks. Current methods do not consider automatic exposure and tone mapping in image signal processing pipeline. We propose a solution to improve the performance of lens flare removal by revisiting the ISP and design a more reliable light sources recovery strategy.
  arXiv  Detail & Related papers  (2023-08-31T04:58:17Z)
• Toward Real Flare Removal: A Comprehensive Pipeline and A New Benchmark [12.1632995709273]
  We propose a well-developed methodology for generating data-pairs with flare deterioration. The similarity of scattered flares and symmetric effect of reflected ghosts are realized. We also construct a real-shot pipeline that respectively processes the effects of scattering and reflective flares.
  arXiv  Detail & Related papers  (2023-06-28T02:57:25Z)
• CamDiff: Camouflage Image Augmentation via Diffusion Model [83.35960536063857]
  CamDiff is a novel approach to synthesize salient objects in camouflaged scenes. We leverage the latent diffusion model to synthesize salient objects in camouflaged scenes. Our approach enables flexible editing and efficient large-scale dataset generation at a low cost.
  arXiv  Detail & Related papers  (2023-04-11T19:37:47Z)
• Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion [51.11295961195151]
  We exploit the characteristics of the foggy image sequence of driving scenes to densify the confident pseudo labels. Based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion scheme. Our scheme helps the adaptive model achieve 51.92% and 53.84% mean intersection-over-union (mIoU) on two publicly available natural foggy datasets.
  arXiv  Detail & Related papers  (2022-06-10T05:16:50Z)
• High-resolution Iterative Feedback Network for Camouflaged Object Detection [128.893782016078]
  Spotting camouflaged objects that are visually assimilated into the background is tricky for object detection algorithms. We aim to extract the high-resolution texture details to avoid the detail degradation that causes blurred vision in edges and boundaries. We introduce a novel HitNet to refine the low-resolution representations by high-resolution features in an iterative feedback manner.
  arXiv  Detail & Related papers  (2022-03-22T11:20:21Z)

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.