GN-FR:Generalizable Neural Radiance Fields for Flare Removal
- URL: http://arxiv.org/abs/2412.08200v2
- Date: Wed, 18 Dec 2024 09:36:47 GMT
- Title: GN-FR:Generalizable Neural Radiance Fields for Flare Removal
- Authors: Gopi Raju Matta, Rahul Siddartha, Rongali Simhachala Venkata Girish, Sumit Sharma, Kaushik Mitra,
- Abstract summary: We propose a framework to render flare-free views from a sparse set of input images affected by lens flare.
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.
- Score: 11.646119341279164
- License:
- Abstract: Flare, an optical phenomenon resulting from unwanted scattering and reflections within a lens system, presents a significant challenge in imaging. The diverse patterns of flares, such as halos, streaks, color bleeding, and haze, complicate the flare removal process. Existing traditional and learning-based methods have exhibited limited efficacy due to their reliance on single-image approaches, where flare removal is highly ill-posed. We address this by framing flare removal as a multi-view image problem, taking advantage of the view-dependent nature of flare artifacts. This approach leverages information from neighboring views to recover details obscured by flare in individual images. Our proposed framework, GN-FR (Generalizable Neural Radiance Fields for Flare Removal), can render flare-free views from a sparse set of input images affected by lens flare and generalizes across different scenes in an unsupervised manner. GN-FR incorporates several modules within the Generalizable NeRF Transformer (GNT) framework: Flare-occupancy Mask Generation (FMG), View Sampler (VS), and Point Sampler (PS). To overcome the impracticality of capturing both flare-corrupted and flare-free data, we introduce a masking loss function that utilizes mask information in an unsupervised setting. Additionally, 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. To our knowledge, this is the first work to address flare removal within a Neural Radiance Fields (NeRF) framework.
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.
Existing methods are specialized for one specific type only, and overlook the simultaneous occurrence of multiple typed lens flares.
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) - MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal [39.70102431268123]
We propose a lightweight Multi-Frequency Deflare Network (MFDNet) based on the Laplacian Pyramid.
Our network decomposes the flare-corrupted image into low and high-frequency bands, effectively separating the illumination and content information in the image.
Experimental results demonstrate that our approach outperforms state-of-the-art methods in removing nighttime flare on real-world and synthetic images.
arXiv Detail & Related papers (2024-06-26T05:31:36Z) - 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) - Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare
Removal and Beyond [77.72043833102191]
We introduce the first comprehensive nighttime flare removal dataset, consisting of 962 real-captured flare images (Flare-R) and 7,000 synthetic flares (Flare7K)
Compared to Flare7K, Flare7K++ is particularly effective in eliminating complicated degradation around the light source, which is intractable by using synthetic flares alone.
To address this issue, we additionally provide the annotations of light sources in Flare7K++ and propose a new end-to-end pipeline to preserve the light source while removing lens flares.
arXiv Detail & Related papers (2023-06-07T08:27:44Z) - Nighttime Smartphone Reflective Flare Removal Using Optical Center
Symmetry Prior [81.64647648269889]
Reflective flare is a phenomenon that occurs when light reflects inside lenses, causing bright spots or a "ghosting effect" in photos.
We propose an optical center symmetry prior, which suggests that the reflective flare and light source are always symmetrical around the lens's optical center.
We create the first reflective flare removal dataset called BracketFlare, which contains diverse and realistic reflective flare patterns.
arXiv Detail & Related papers (2023-03-27T09:44:40Z) - Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields [65.96818069005145]
Vanilla NeRF is viewer-centred simplifies the rendering process only as light emission from 3D locations in the viewing direction.
Inspired by the emission theory of ancient Greeks, we make slight modifications on vanilla NeRF to train on multiple views of low-light scenes.
We introduce a surrogate concept, Concealing Fields, that reduces the transport of light during the volume rendering stage.
arXiv Detail & Related papers (2023-03-10T09:28:09Z) - Flare7K: A Phenomenological Nighttime Flare Removal Dataset [83.38205781536578]
We introduce Flare7K, the first nighttime flare removal dataset.
It offers 5,000 scattering and 2,000 reflective flare images, consisting of 25 types of scattering flares and 10 types of reflective flares.
With the paired data, we can train deep models to restore flare-corrupted images taken in the real world effectively.
arXiv Detail & Related papers (2022-10-12T20:17:24Z) - How to Train Neural Networks for Flare Removal [45.51943926089249]
We train neural networks to remove lens flare for the first time.
Our data synthesis approach is critical for accurate flare removal.
Models trained with our technique generalize well to real lens flares across different scenes, lighting conditions, and cameras.
arXiv Detail & Related papers (2020-11-25T02:23:50Z)
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.