• Publications
  • Influence
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
tl;dr
We propose a novel image denoising strategy based on an enhanced sparse representation in transform domain. Expand
  • 4,930
  • 970
Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction
tl;dr
We present an extension of the BM3D filter to volumetric data. Expand
  • 406
  • 121
Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images
tl;dr
The shape-adaptive discrete cosine transform (SA-DCT) transform can be computed on a support of arbitrary shape, but retains a computational complexity comparable to that of the usual separable block- DCT. Expand
  • 570
  • 83
BM3D Image Denoising with Shape-Adaptive Principal Component Analysis
We propose an image denoising method that ex- ploits nonlocal image modeling, principal component analysis (PCA), and local shape-adaptive anisotropic estimation. The nonlocal modeling is exploitedExpand
  • 388
  • 83
BM3D Frames and Variational Image Deblurring
tl;dr
In this paper, we construct analysis and synthesis frames, formalizing BM3D image modeling, and use these frames to develop novel iterative deblurring algorithms. Expand
  • 411
  • 70
Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-Image Raw-Data
tl;dr
We present a simple and usable noise model for the raw-data of digital imaging sensors, which gives the pointwise standard-deviation of the noise as a function of the expectation of the pixel raw data output. Expand
  • 476
  • 66
Color Image Denoising via Sparse 3D Collaborative Filtering with Grouping Constraint in Luminance-Chrominance Space
tl;dr
We propose an effective color image denoising method that exploits filtering in highly sparse local 3D transform domain in each channel of a luminance-chrominance color space. Expand
  • 259
  • 63
Image denoising with block-matching and 3D filtering
We present a novel approach to still image denoising based on effective filtering in 3D transform domain by combining sliding-window transform processing with block-matching. We process blocks withinExpand
  • 446
  • 56
Image restoration by sparse 3D transform-domain collaborative filtering
tl;dr
We propose an image restoration technique exploiting regularized inversion and the recent block-matching and 3D filtering (BM3D) denoising filter to improve the regularization after inversion in discrete Fourier domain. Expand
  • 335
  • 52
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results
tl;dr
This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. Expand
  • 434
  • 41