Large-Scale Methods in Image Deblurring

Scale-recurrent Network for Deep Image Deblurring

In single image deblurring, the “coarse-to-fine” scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-networkbased approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many rece...

Total variation image deblurring with space-varying kernel

Image deblurring techniques based on convex optimization formulations, such as total-variation deblurring, often use specialized first-order methods for large-scale nondifferentiable optimization. A key property exploited in these methods is spatial invariance of the blurring operator, which makes it possible to use the fast Fourier transform (FFT) when solving linear equations involving the op...

Domain decomposition method for image deblurring

As a fundamental problem in image processing, image deblurring has still attracted a lot of research attention. Due to the large computational cost, especially for high-resolution images, it becomes challenging to solve the deblurring minimization problem and the underlying partial differential equations. The domain decomposition method (DD), as one of themost efficient algorithms for solving l...

Large-Scale Image Deblurring in Java

This paper describes Parallel Spectral Deconvolution (PSD) Java software for image deblurring. A key component of the software, JTransforms, is the first, open source, multithreaded FFT library written in pure Java. Benchmarks show that JTransforms is competitive with current C implementations, including the well-known FFTW package. Image deblurring examples, including performance comparisons w...

Adaptive Varying Scale Methods in Image Processing Part I: Denoising and Deblurring

Scale Adaptive Blind Deblurring

The presence of noise and small scale structures usually leads to large kernel estimation errors in blind image deblurring empirically, if not a total failure. We present a scale space perspective on blind deblurring algorithms, and introduce a cascaded scale space formulation for blind deblurring. This new formulation suggests a natural approach robust to noise and small scale structures throu...