Is Denoising Dead?

By Priyam Chatterjee, Peyman Milanfar. 2010

475 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising (2019, background): “Owing to the fact that noise corruption always occurs in the image sensing process and may degrade the visual quality of collected images, image denoising is needed for various computer vision tasks [2].”
The Perception-Distortion Tradeoff (2017, background): “Several past works attempted to answer the question: What is the minimal attainable distortion Dmin in various restoration tasks? [49], [50], [51], [52], [53].”
Toward Convolutional Blind Denoising of Real Photographs (2018, background): “With decades of studies, numerous promising approaches [3, 12, 17, 53, 11, 61] have been developed and near-optimal performance [8, 31, 50] has been achieved for the removal of additive white Gaussian noise (AWGN).”
PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds (2019, background): “In signal processing literature, it is widely believed that image de-noising has reached close to optimal performance [CM10,LN11].”
A Nonlocal Bayesian Image Denoising Algorithm (2013, background): “Two types of performance bounds proposed in [28] and [8] address the same class of patchbased algorithms and propose denoising methods approaching these bounds (section 3).”
Real Image Denoising With Feature Attention (2019, background): “[16], motivated external denoising [9, 7, 42, 62] by showing that an image can be recovered with negligible error by selecting reference patches from a clean external database.”
The Little Engine That Could: Regularization by Denoising (RED) (2016, background): “For instance, instead of ρ ( x ) = (cid:107) x 21 , consider ρ D ( x ) = (cid:107) Dx 21 .”
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising (2017, background): “Removing noise from the observed image is an essential step in various image processing and computer vision tasks [1], [2].”
Image denoising with multi-layer perceptrons, part 2: training trade-offs and analysis of their mechanisms (2012, background): “In addition, the MLPs outperform one type of theoretical bound in image denoising (Chatterjee and Milanfar, 2010) and come a long way toward closing the gap to a second type of theoretical bound (Levin et al., 2012).”
Natural image denoising: Optimality and inherent bounds (2011, background): “An interesting question for future research, as recently considered by [5, 6], is whether there is a significant advantage in adapting the prior to the specific statistics of the observed image, as done by some recent denoising algorithms [3, 10, 8].”
CycleISP: Real Image Restoration via Improved Data Synthesis (2020, result): “For many years the patch-based methods yielded comparable results, thus prompting studies [11, 12, 37] to investigate whether we reached the theoretical limits of denoising performance.”
Patch Complexity, Finite Pixel Correlations and Optimal Denoising (2012, background): “In [15] we show that this is implicit in several recent works, consistent with [7].”
An Analysis and Implementation of the BM3D Image Denoising Method (2012, background): “It is furthermore interesting to notice that recent papers [3, 14] which try to evaluate the inherent bounds of patch-based denoising methods claim that BM3D is really close to those optimality bounds.”