Noise Estimation from a Single Image

By Ce Liu, William T. Freeman, Richard Szeliski, Sing Bing Kang. Computer Vision and Pattern Recognition, 2006

407 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e557d18437bab303ec13c4159ce82bac3de1a7e9

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Single image dehazing (2008, methodology): “Recently [Liu et al. 2006] proposed an automated method to estimate the noise level based on a single image.”
Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration (2007, background): “σnoise can be estimated in a number of ways ([7]), e.”
Eulerian video magnification for revealing subtle changes in the world (2012, methodology): “The noise power 2 can be estimated by examining pixel values in a stable region of the scene, from a gray card, or by using a technique as in [Liu et al. 2006].”
Image Blind Denoising with Generative Adversarial Network Based Noise Modeling (2018, unknown): “level estimated by algorithms like [19, 37, 17].”
Unsupervised feature learning framework for no-reference image quality assessment (2012, background): “For example, image processing and transmission systems may have their parameters be adjusted according to the image quality [9]; image retrieval systems can use quality as an attribute to rank images and image processing algorithms may use image quality measures for evaluation.”
Sparse Representation for Color Image Restoration (2008, methodology): “The alternative path, a nonparametric learning, uses image examples directly within the reconstruction process, as practiced by Efros and Leung for texture synthesis [33], by Freeman et al. for super-resolution [34], [35], and by several follow-up works [36]–[39] for super-resolution and inpainting.”
A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach (2006, methodology): “It has been adopted for several applications such as image denoising (Tomasi and Manduchi 1998; Liu et al. 2006), relighting and texture manipulation (Oh et al.”
PSF estimation using sharp edge prediction (2008, unknown): “[9], and we have empirically found λ = 2 to work well.”
Beyond pixels: exploring new representations and applications for motion analysis (2009, background): “Freeman, I studied automatically estimating noise level functions (NLFs) from a single color image [64] and applying NLFs for automatic noise removal [66].”
Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-Image Raw-Data (2008, methodology): “Heuristic models for σ, such as those found using the principal component analysis in [11], can also be exploited in our estimation framework.”
Guided Image Filtering (2010, methodology): “It has been widely used in noise reduction [28], HDR compression [15], multiscale detail decomposition [29], and image abstraction [30].”
Face Hallucination: Theory and Practice (2007, methodology): “Inspired by the adaptive bilateral filtering work [23], we design the parameters of the bilateral filter to be dependent on image coordinates.”
Image deblurring with blurred/noisy image pairs (2007, background): “The noisy image is usually underexposed and has a very low SNR since camera noise is dependent on the image intensity level [Liu et al. 2006].”
Blind Quality Assessment Based on Pseudo-Reference Image (2018, background): “[28] inferred the noise as a function of image intensity from a”
A Bilevel Optimization Approach for Parameter Learning in Variational Models (2013, background): “We point out that this assumption is reasonable also for practical problems since in many cases, the noise level can be computed from the image acquisition process, can be specified by the user, or can be estimated by separate algorithms [19].”