Efficient Deblurring for Shaken and Partially Saturated Images

2023-11-23 18:20

本文主要是介绍Efficient Deblurring for Shaken and Partially Saturated Images,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

Try the online demo: http://willow-fd.rocq.inria.fr/unshake/

Overview

One common feature of “shaken” images is the presence of saturated pixels. These are caused when the radiance of the scene exceeds the range of the camera’s sensor, leaving bright highlights clipped at the maximum output value (e.g. 255 for an 8-bit image). To anyone who has attempted to take hand-held photographs at night, this effect should be familiar as the conspicuous bright streaks left by electric lights, such as in the images below. These bright pixels, with their clipped values, violate the assumption made by many algorithms that the image formation process is linear, and as a result can cause obtrusive artifacts in the deblurred images. This can be seen in the example images below. In this paper, we propose a non-blind deblurring algorithm that takes account of saturated pixels, and is able to greatly reduce the artifacts they cause in the deblurred results.


We also demonstrate an efficient approximation for spatially-varying blur, extending the work of Hirsch et al. [4] to handle our previously-proposed global model for spatially-varying camera shake blur [5]. This approximation, based on the local uniformity of the blur, allows the forward model for spatially-varying blur to be computed significantly faster than the exact model, while retaining the benefits of the global parameterization. Note that independently of our work, Hirsch et al. [6] have proposed a similar method to combine a global model of spatially-varying blur with their locally-uniform approximation.

Examples

Click to enlarge images. Navigate through with cursor keys.

  • Blurry image with saturation

  • Deblurred with Richardson-Lucy [1,2]

  • Deblurred with algorithm of Krishnan & Fergus [3]

  • Deblurred with proposed method

  • Blurry image with saturation
  • Deblurred with Richardson-Lucy [1,2]
  • Deblurred with algorithm of Krishnan & Fergus [3]
  • Deblurred with proposed method
  • Blurry image with saturation
  • Deblurred with Richardson-Lucy [1,2]
  • Deblurred with algorithm of Krishnan & Fergus [3]
  • Deblurred with proposed method
  • Blurry image with saturation
  • Deblurred with Richardson-Lucy [1,2]
  • Deblurred with algorithm of Krishnan & Fergus [3]
  • Deblurred with proposed method
  • Blurry image with saturation
  • Deblurred with Richardson-Lucy [1,2]
  • Deblurred with algorithm of Krishnan & Fergus [3]
  • Deblurred with proposed method

Efficient Approximation of the Global Blur Model

The images below show a synthetic blur kernel for our previously proposed model [5]. The PSF is visualized at various points across the image, using the exact forward model and the approximation at increasingly fine levels of discretization. The approximation quickly approaches the exact model, and at the finest discretization shown it is almost identical to the exact model.

  • Global blur kernel

    Global blur kernel

  • Exact forward model

    PSF, exact forward model

  • Approximate forward model, 3 × 4 patches

    PSF, approximate forward model,
    3 × 4 patches

  • Approximate forward model, 6 × 8 patches

    PSF, approximate forward model,
    6 × 8 patches

  • Approximate forward model, 12 × 16 patches

    PSF, approximate forward model,
    12 × 16 patches

Paper

O. Whyte, J. Sivic and A. Zisserman
Deblurring Shaken and Partially Saturated Images
IEEE Color and Photometry in Computer Vision Workshop (2011), in conjunction with ICCV 2011
PDF  | Abstract | BibTeX | PPT Slides (19MB)
O. Whyte, J. Sivic and A. Zisserman
Deblurring Shaken and Partially Saturated Images
International Journal of Computer Vision, 2014
PDF  | Abstract | BibTeX | Journal page

Images

The images from the CPCV 2011 paper: Download (25MB)

The results of our algorithm on the images of Cho et al. [7]: Download (16MB)

Code

A package of Matlab code for non-blind deblurring of blurry images with clipped / saturated pixels.
Version 0.1 (20-Nov-2011): Download (7MB) | Readme

Code

This package contains code to perform fast blind deblurring of images degraded by camera shake, using the MAP algorithm described in our IJCV 2012 paper, and the fast approximation of spatially-varying blur described in our CPCV 2011 paper. 

Version 1.0 (21-Sep-2014): Download (18MB) | Readme 

 

Comparison to the Method of Cho et al.

The images below show the results of our non-blind deblurring algorithm on images provided by Cho et al. [7]. The (spatially-invariant) blur kernels for the images, along with the results of their algorithm, are provided by the authors online here.

Download the uncompressed images above, or at this link.

Click to enlarge images. Navigate through with cursor keys.

  • Blurry Image

  • Result from Cho et al. [7]

  • Our result

  • Blurry Image
  • Result of Cho et al.
  • Our result
  • Blurry Image
  • Result of Cho et al.
  • Our result
  • Blurry Image
  • Result of Cho et al.
  • Our result
  • Blurry Image
  • Result of Cho et al.
  • Our result
  • Blurry Image
  • Result of Cho et al.
  • Our result
  • Blurry Image
  • Result of Cho et al.
  • Our result

References

[1] W. H. Richardson. Bayesian-Based Iterative Method of Image Restoration. Journal of the Optical Society of America, 62(1), 1972.

[2] L. B. Lucy. An iterative technique for the rectification of observed distributions. Astronomical Journal, 79(6), 1974.

[3] D. Krishnan and R. Fergus. Fast Image Deconvolution using Hyper-Laplacian Priors. In Proc. NIPS, 2009.

[4] M. Hirsch, S. Sra, B. Scholkopf, and S. Harmeling. Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution. In Proc. CVPR, 2010.

[5] O. Whyte, J. Sivic, A. Zisserman, and J. Ponce. Non-uniform Deblurring for Shaken Images. In Proc. CVPR, 2010.

[6] M. Hirsch, C. J. Schuler, S. Harmeling, and B. Schölkopf. Fast Removal of Non-uniform Camera Shake. In Proc. ICCV, 2011.

[7] S. Cho, J. Wang, and S. Lee. Handling Outliers in Non-blind Image Deconvolution. In Proc. ICCV, 2011.

转载于:https://www.cnblogs.com/ywsoftware/p/4511811.html

这篇关于Efficient Deblurring for Shaken and Partially Saturated Images的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/419860

相关文章

[论文笔记]QLoRA: Efficient Finetuning of Quantized LLMs

引言 今天带来LoRA的量化版论文笔记——QLoRA: Efficient Finetuning of Quantized LLMs 为了简单,下文中以翻译的口吻记录,比如替换"作者"为"我们"。 我们提出了QLoRA,一种高效的微调方法,它在减少内存使用的同时,能够在单个48GB GPU上对65B参数的模型进行微调,同时保持16位微调任务的完整性能。QLoRA通过一个冻结的4位量化预

docker images

docker 装好docker之后,先掌握一下docker启动与停止 docker启动关闭状态 systemctl 命令是系统服务管理器指令,它是 service 和 chkconfig 两个命令组合。 查看 docker 的启动状态 systemctl status docker 关闭 docker systemctl stop docker 启动 docker syste

k8s执行crictl images报错

FATA[0000] validate service connection: CRI v1 image API is not implemented for endpoint "unix:///run/containerd/containerd.sock": rpc error: code = Unimplemented desc = unknown service runtime.v1.Ima

《Efficient Batch Processing for Multiple Keyword Queries on Graph Data》——论文笔记

ABSTRACT 目前的关键词查询只关注单个查询。对于查询系统来说,短时间内会接受大批量的关键词查询,往往不同查询包含相同的关键词。 因此本文研究图数据多关键词查询的批处理。为多查询和单个查询找到最优查询计划都是非常复杂的。我们首先提出两个启发式的方法使关键词的重叠最大并优先处理规模小的关键词。然后设计了一个同时考虑了数据统计信息和搜索语义的基于cardinality的成本估计模型。 1.

《The Power of Scale for Parameter-Efficient Prompt Tuning》论文学习

系列文章目录 文章目录 系列文章目录一、这篇文章主要讲了什么?二、摘要中T5是什么1、2、3、 三、1、2、3、 四、1、2、3、 五、1、2、3、 六、1、2、3、 七、1、2、3、 八、1、2、3、 一、这篇文章主要讲了什么? The article “The Power of Scale for Parameter-Efficient Prompt Tuning

mkimage command not found - U-Boot images will not be

ubuntu14.04编译内核报错: "mkimage" command not found - U-Boot images will not be built make[1]: *** [arch/arm/boot/uImage] Error 1 make: *** [uImage] Error 2 按照错误提示安装uboot-mkimage # apt-get install uboo

SAM 2: The next generation of Meta Segment Anything Model for videos and images

https://ai.meta.com/blog/segment-anything-2/  https://github.com/facebookresearch/segment-anything-2  https://zhuanlan.zhihu.com/p/712068482

OpenCV-Python 教程——从Images开始

目标 这里,你将会学到如何读取、显示、保存一张图片你将会学习这些函数:cv2.imread(), cv2.imshow(), cv2.imwrite()当然,你将会学习如何用Matplotlib显示这些图片 使用OpenCV 读取图片 利用函数cv2.imread()来读取一张图片。该图片应该在工作目录中或是提供图片的绝对路径。 第二个参数用来明确读取图片的方式。 cv2.IMREAD

DynamiCrafter:Animating open-domain images with video diffusion priors

1.Method 图像条件视频生成, 1.1 Image Dynamics from Video Diffusion Priors 1.1.1 文本对齐的上下文表征 文本嵌入通过clip构建,图像通过clip编码,主要代表语义层面的视觉内容,未能捕获图像的完整信息,为了提取更完整的信息,使用来自clip图像vit最后一层的全视觉标记,该token在条件图像生成时表现出了高保真度,为

论文阅读:VideoMamba: State Space Model for Efficient Video Understanding

论文地址:arxiv 摘要 为了解决视频理解中的局部冗余与全局依赖性的双重挑战。作者将 Mamba 模型应用于视频领域。所提出的 VideoMamba 克服了现有的 3D 卷积神经网络与视频 Transformer 的局限性。 经过广泛的评估提示了 VideoMamba 的能力: 在视觉领域有可扩展性,无需大规模数据集来预训练。对于短期动作也有敏感性,即使是细微的动作差异也可以识别到在长期视