Denoising by Inpainting

نویسندگان

  • Robin Dirk Adam
  • Pascal Peter
  • Joachim Weickert
چکیده

The filling-in effect of diffusion processes has been successfully used in many image analysis applications. Examples include image reconstructions in inpainting-based compression or dense optic flow computations. As an interesting side effect of diffusion-based inpainting, the interpolated data are smooth, even if the known image data are noisy: Inpainting averages information from noisy sources. Since this effect has not been investigated for denoising purposes so far, we propose a general framework for denoising by inpainting. It averages multiple inpainting results from different selections of known data. We evaluate two concrete implementations of this framework: The first one specifies known data on a shifted regular grid, while the second one employs probabilistic densification to optimise the known pixel locations w.r.t. the inpainting quality. For homogeneous diffusion inpainting, we demonstrate that our regular grid method approximates the quality of its corresponding diffusion filter. The densification algorithm with homogeneous diffusion inpainting, however, shows edge-preserving behaviour. It resembles space-variant diffusion and offers better reconstructions than homogeneous diffusion filters.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Comparison of Dictionary Based Approaches to Inpainting and Denoising with an Emphasis to Independent Component Analysis Learned Dictionaries

The first contribution of this paper is the comparison of learned dictionary based approaches to inpainting and denoising of images in natural scenes, where emphasis is given on the use of complete and overcomplete dictionary learned by independent component analysis. The second contribution of the paper relates to the formulation of a problem of denoising an image corrupted by a salt and peppe...

متن کامل

Image Denoising and Inpainting with Deep Neural Networks

We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA). We propose an alternative training scheme that successfully adapts DA, originally designed for unsupervised feature learning, to the tasks of image denoising and blind inpainting. Our method’s performance in the image denoising task is comparable t...

متن کامل

Denoising and Inpainting of Images Using TV-Type Energies: Theoretical and Computational Aspects

In our note we discuss variational approaches towards the denoising of images and towards the image inpainting problem combined with simultaneous denoising. Our techniques are based on variants of the TV-model but in contrast to this case a complete analytical theory is available in our setting. At the same time, numerical experiments illustrate the advantages of our models in comparison with s...

متن کامل

Image Restoration by Iterative Denoising and Backward Projections

Inverse problems appear in many applications such as image deblurring and inpainting. The common approach to address them is to design a specific algorithm for each problem. The Plug-and-Play (P&P) framework, which has been recently introduced, allows solving general inverse problems by leveraging the impressive capabilities of existing denoising algorithms. While this fresh strategy has found ...

متن کامل

Solving Variational Problems in Image Processing via Projections A Common View on TV Denoising and Wavelet Shrinkage

Variational methods are very common in image processing. They are used for denoising, deblurring, segmentation or inpainting. In this short paper we review a method for the solution of a special class of variational problems, presented in [2]. We show applications to TV denoising and new applications to total variation deblurring, wavelet shrinkage and texture extraction. Moreover this approach...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017