首页/论文/2012.14678

arXiv 2012.146782020-12-29cs.CVeess.IV

Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy

Xi’an Jiaotong University（西安交通大学）；University of Virginia（弗吉尼亚大学）；Hikvision（海康威视）

Shuang Xu, Lizhen Ji, Zhe Wang, Pengfei Li, Kai Sun, Chunxia Zhang, Jiangshe Zhang

发表信息：: IEEE Transactions on Computational Imaging, vol. 6, pp. 1561-1570, 2020
DOI：: 10.1109/TCI.2020.3039564

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Multi-focus image fusion (MFF) is a popular technique to generate an all-in-focus image, where all objects in the scene are sharp. However, existing methods pay little attention to defocus spread effects of the real-world multi-focus images. Consequently, most of the methods perform badly in the areas near focus map boundaries. According to the idea that each local region in the fused image should be similar to the sharpest one among source images, this paper presents an optimization-based approach to reduce defocus spread effects. Firstly, a new MFF assessmentmetric is presented by combining the principle of structure similarity and detected focus maps. Then, MFF problem is cast into maximizing this metric. The optimization is solved by gradient ascent. Experiments conducted on the real-world dataset verify superiority of the proposed model. The codes are available at https://github.com/xsxjtu/MFF-SSIM.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Point Spread Function Estimation of Defocus

Chongqing University（重庆大学）

This Point spread function (PSF) plays a crucial role in many computational imaging applications, such as shape from focus/defocus, depth estimation, and fluorescence microscopy. However, the mathematical model of the defocus process is still unclear. In this work, we develop an alternative method to estimate the precise mathematical model of the point spread function to describe the defocus process. We first derive the mathematical algorithm for the PSF which is used to generate the simulated focused images for different focus depth. Then we compute the loss function of the similarity between…

2022-09-19cs.CVeess.IV

MFFW: A new dataset for multi-focus image fusion

Xi’an Jiaotong University（西安交通大学）

Multi-focus image fusion (MFF) is a fundamental task in the field of computational photography. Current methods have achieved significant performance improvement. It is found that current methods are evaluated on simulated image sets or Lytro dataset. Recently, a growing number of researchers pay attention to defocus spread effect, a phenomenon of real-world multi-focus images. Nonetheless, defocus spread effect is not obvious in simulated or Lytro datasets, where popular methods perform very similar. To compare their performance on images with defocus spread effect, this paper constructs a ne…

2020-02-12cs.CVcs.MM

SVBR-NET: A Non-Blind Spatially Varying Defocus Blur Removal Network

Trinity College Dublin（都柏林圣三一学院）；ADAPT: SFI Centre for Digital Media Technology（ADAPT：SFI数字媒体技术中心）；Federal University of Rio Grande Do Sul（南里奥格兰德联邦大学）

Defocus blur is a physical consequence of the optical sensors used in most cameras. Although it can be used as a photographic style, it is commonly viewed as an image degradation modeled as the convolution of a sharp image with a spatially-varying blur kernel. Motivated by the advance of blur estimation methods in the past years, we propose a non-blind approach for image deblurring that can deal with spatially-varying kernels. We introduce two encoder-decoder sub-networks that are fed with the blurry image and the estimated blur map, respectively, and produce as output the deblurred (deconvolv…

2022-06-26cs.CVeess.IV

一种基于α-Matte边界散焦模型的级联网络用于多聚焦图像融合

An α-Matte Boundary Defocus Model Based Cascaded Network for Multi-focus Image Fusion

Tsinghua University（清华大学）；Hong Kong University of Science and Technology（香港科技大学）；University College London（伦敦大学学院）

针对多聚焦图像融合中聚焦/散焦边界区域结果不清晰的问题，提出α-matte边界散焦模型生成训练数据，并构建级联边界感知网络MMF-Net，实现了优于现有方法的融合效果。

2019-10-30cs.CV

MFIF-GAN: A New Generative Adversarial Network for Multi-Focus Image Fusion

Xi’an Jiaotong University（西安交通大学）

Multi-Focus Image Fusion (MFIF) is a promising image enhancement technique to obtain all-in-focus images meeting visual needs and it is a precondition of other computer vision tasks. One of the research trends of MFIF is to avoid the defocus spread effect (DSE) around the focus/defocus boundary (FDB). In this paper,we propose a network termed MFIF-GAN to attenuate the DSE by generating focus maps in which the foreground region are correctly larger than the corresponding objects. The Squeeze and Excitation Residual module is employed in the network. By combining the prior knowledge of training …

2020-11-09cs.CV

End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation

University of Padova（帕多瓦大学）；Sony Europe B.V.（索尼欧洲有限公司）

Monocular depth estimation is still an open challenge due to the ill-posed nature of the problem at hand. Deep learning based techniques have been extensively studied and proved capable of producing acceptable depth estimation accuracy even if the lack of meaningful and robust depth cues within single RGB input images severally limits their performance. Coded aperture-based methods using phase and amplitude masks encode strong depth cues within 2D images by means of depth-dependent Point Spread Functions (PSFs) at the price of a reduced image quality. In this paper, we propose a novel end-to-e…

2022-04-14cs.CVeess.IV

更多相关论文收起更多论文

Learning to Estimate Kernel Scale and Orientation of Defocus Blur with Asymmetric Coded Aperture

Tsinghua University（清华大学）；Research Institute of Tsinghua University in Shenzhen（清华大学深圳研究院）；Boyan Technology DBA RayShaper China（博研科技（商业名称为RayShaper中国））

Consistent in-focus input imagery is an essential precondition for machine vision systems to perceive the dynamic environment. A defocus blur severely degrades the performance of vision systems. To tackle this problem, we propose a deep-learning-based framework estimating the kernel scale and orientation of the defocus blur to adjust lens focus rapidly. Our pipeline utilizes 3D ConvNet for a variable number of input hypotheses to select the optimal slice from the input stack. We use random shuffle and Gumbel-softmax to improve network performance. We also propose to generate synthetic defocuse…

2021-03-10cs.CVcs.MMeess.IV

用于多聚焦图像融合的清晰度对比与相似性选择

Clarity Contrast and Similarity Selection for Multi-Focus Image Fusion

该研究针对多聚焦图像融合中源图像交互不足的问题，提出CSNet模型，通过CCAM和相似性选择策略实现信息交互，在定量和定性评估中达到当前最优性能。

2026-08-05cs.CV

面向像差感知散焦深度估计的自监督空间变化PSF估计

Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus

Tokyo Institute of Technology（东京工业大学）

针对真实相机空间变化PSF难以标定的问题，提出利用清晰/模糊图像对的自监督PSF估计方法，引入旋转对称假设、极坐标建模并处理对焦呼吸，提升DfD深度估计性能。

2024-02-28cs.CVeess.IV

Improving Image Restoration by Revisiting Global Information Aggregation

MEGVII Technology（旷视科技）

Global operations, such as global average pooling, are widely used in top-performance image restorers. They aggregate global information from input features along entire spatial dimensions but behave differently during training and inference in image restoration tasks: they are based on different regions, namely the cropped patches (from images) and the full-resolution images. This paper revisits global information aggregation and finds that the image-based features during inference have a different distribution than the patch-based features during training. This train-test inconsistency negat…

2022-08-02cs.CVeess.IV

频率驱动的逆核预测用于单图像散焦去模糊

Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring

本文提出频率驱动的逆核预测网络FDIKP，结合双分支逆核预测、位置自适应卷积和双域尺度循环模块，从粗到细提升单图像散焦去模糊性能。

2025-08-18cs.CV

Analysis of the noise in back-projection light field acquisition and its optimization

Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences（中国科学院上海光学精密机械研究所）；The University of Hong Kong（香港大学）

Light field reconstruction from images captured by focal plane sweeping can achieve high lateral resolution comparable to the modern camera sensor. This is impossible for the conventional micro-lenslet based light field capture systems. However, the severe defocus noise and the low depth resolution limit its applications. In this paper, we analyze the defocus noise and the depth resolution in the focal plane sweeping based light field reconstruction technique, and propose a method to reduce the defocus noise and improve the depth resolution. Both numerical and experimental results verify the p…

2016-12-30cs.CVphysics.optics

Single Image Depth Estimation Trained via Depth from Defocus Cues

Tel Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）

Estimating depth from a single RGB images is a fundamental task in computer vision, which is most directly solved using supervised deep learning. In the field of unsupervised learning of depth from a single RGB image, depth is not given explicitly. Existing work in the field receives either a stereo pair, a monocular video, or multiple views, and, using losses that are based on structure-from-motion, trains a depth estimation network. In this work, we rely, instead of different views, on depth from focus cues. Learning is based on a novel Point Spread Function convolutional layer, which applie…

2020-01-14cs.CV

Adaptive Weighting Depth-variant Deconvolution of Fluorescence Microscopy Images with Convolutional Neural Network

University of Michigan-Shanghai Jiao Tong University Joint Institute（上海交通大学密西根学院）；Shanghai Jiao Tong University（上海交通大学）

Fluorescence microscopy plays an important role in biomedical research. The depth-variant point spread function (PSF) of a fluorescence microscope produces low-quality images especially in the out-of-focus regions of thick specimens. Traditional deconvolution to restore the out-of-focus images is usually insufficient since a depth-invariant PSF is assumed. This article aims at handling fluorescence microscopy images by learning-based depth-variant PSF and reducing artifacts. We propose adaptive weighting depth-variant deconvolution (AWDVD) with defocus level prediction convolutional neural net…

2019-07-07cs.CVeess.IV

点云中的鬼影：瞬态域中的LiDAR去眩光

Ghosts in the Point Clouds: De-glaring LiDAR in the Transient Domain

University of Wisconsin–Madison（威斯康星大学麦迪逊分校）

针对固态LiDAR内部多径眩光导致的伪影问题，提出基于瞬态眩光扩散函数（TGSF）的物理模型和无训练算法，在点云形成前抑制眩光，保留真实场景结构。

2026-05-23cs.CV

Leveraging blur information for plenoptic camera calibration

Université Clermont Auvergne（克莱蒙奥弗涅大学）；Clermont Auvergne INP（克莱蒙奥弗涅国立综合理工学院）；CNRS（法国国家科学研究中心）；Cerema（法国环境与风险研究中心）

This paper presents a novel calibration algorithm for plenoptic cameras, especially the multi-focus configuration, where several types of micro-lenses are used, using raw images only. Current calibration methods rely on simplified projection models, use features from reconstructed images, or require separated calibrations for each type of micro-lens. In the multi-focus configuration, the same part of a scene will demonstrate different amounts of blur according to the micro-lens focal length. Usually, only micro-images with the smallest amount of blur are used. In order to exploit all available…

2021-11-09cs.CVeess.IV

通过下一步聚焦预测进行视觉自回归建模

FVAR: Visual Autoregressive Modeling via Next Focus Prediction

Baidu Inc.（百度公司）

FVAR通过引入下一步聚焦预测范式，改进多尺度自回归模型以减少混叠伪影并提升细节生成质量。

2025-11-24cs.CV

A Method For Adding Motion-Blur on Arbitrary Objects By using Auto-Segmentation and Color Compensation Techniques

Hiroshima City University（广岛市立大学）；Kyushu University（九州大学）

When dynamic objects are captured by a camera, motion blur inevitably occurs. Such a blur is sometimes considered as just a noise, however, it sometimes gives an important effect to add dynamism in the scene for photographs or videos. Unlike the similar effects, such as defocus blur, which is now easily controlled even by smartphones, motion blur is still uncontrollable and makes undesired effects on photographs. In this paper, an unified framework to add motion blur on per-object basis is proposed. In the method, multiple frames are captured without motion blur and they are accumulated to cre…

2021-09-22cs.CV