Turbo denoising for mobile photographic applications

Wong, Tak-Shing; Milanfar, Peyman

doi:10.1109/icip.2016.7532505

Cited by 6 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 15: Tuning spatial parameter of Turbo denoising [44] by using our proposed quality assessment model NIMA(VGG16). Standard deviation of the additive white Gaussian noise is set as 30.…”

Section: Discussionmentioning

confidence: 99%

“…Perceptual tuning could be quite expensive and time consuming, especially when human opinion is required. In this section, our proposed models are (a) 6.38 (7.16) (b) 6.24 (6.79) (c) 6 Kim et al [16] 0.80 0.80 ---Moorthy et al [39] 0.89 0.88 ---Mittal et al [40] 0.92 0.89 ---Saad et al [41] 0.91 0.88 ---Kottayil et al [42] 0.89 0.88 ---Xu et al [35] 0.96 0.95 ---Bianco et al [7] 0 used to tune a tone enhancement method [43], and an image denoiser [44]. A more detailed treatment is presented in [23].…”

Section: Image Enhancementmentioning

confidence: 99%

See 1 more Smart Citation

NIMA: Neural Image Assessment

Talebi

Milanfar

2018

IEEE Trans. on Image Process.

Self Cite

806

467

View full text Add to dashboard Cite

Automatically learned quality assessment for images has recently become a hot topic due to its usefulness in a wide variety of applications such as evaluating image capture pipelines, storage techniques and sharing media. Despite the subjective nature of this problem, most existing methods only predict the mean opinion score provided by datasets such as AVA [1] and TID2013 [2]. Our approach differs from others in that we predict the distribution of human opinion scores using a convolutional neural network. Our architecture also has the advantage of being significantly simpler than other methods with comparable performance. Our proposed approach relies on the success (and retraining) of proven, state-of-the-art deep object recognition networks. Our resulting network can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms in a photographic pipeline. All this is done without need for a "golden" reference image, consequently allowing for single-image, semantic- and perceptually-aware, no-reference quality assessment.

show abstract

“…Fig. 15: Tuning spatial parameter of Turbo denoising [44] by using our proposed quality assessment model NIMA(VGG16). Standard deviation of the additive white Gaussian noise is set as 30.…”

Section: Discussionmentioning

confidence: 99%

Section: Image Enhancementmentioning

confidence: 99%

NIMA: Neural Image Assessment

Talebi

Milanfar

2018

IEEE Trans. on Image Process.

Self Cite

806

467

View full text Add to dashboard Cite

show abstract

“…[64] Given a patch P i and its block circulant representation bcirc(P) in (15), there exists an orthogonal matrix F ⊗ I that could transform bcirc(P) into a block diagonal matrix via bdiag(P) = (F ⊗ I)bcirc(P)(F ⊗ I) −1 (28) where ⊗ represents the kronecker product, andP = P × 3 W, W = √ 3F. Furthermore, according to the orthogonality, we have C f diag F = C bcirc F (29)…”

Section: Appendix B Re-formulation Of Block Circulant Tensor Decomposmentioning

confidence: 99%

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

Kong

Yang

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Filtering images of more than one channel is challenging in terms of both efficiency and effectiveness. By grouping similar patches to utilize the self-similarity and sparse linear approximation of natural images, recent nonlocal and transformdomain methods have been widely used in color and multispectral image (MSI) denoising. Many related methods focus on the modeling of group level correlation to enhance sparsity, which often resorts to a recursive strategy with a large number of similar patches. The importance of the patch level representation is understated. In this paper, we mainly investigate the influence and potential of representation at patch level by considering a general formulation with block diagonal matrix. We further show that by training a proper global patch basis, along with a local principal component analysis transform in the grouping dimension, a simple transform-threshold-inverse method could produce very competitive results. Fast implementation is also developed to reduce computational complexity. Extensive experiments on both simulated and real datasets demonstrate its robustness, effectiveness and efficiency.

show abstract

“…Intel and the Intel logo are trademarks of Intel Corporation in the U.S. and/or other countries. © Intel Corporation For demosaic, reference RGB image and its corresponding Bayer image can be simulated by adding noise on linearized clean RGB image using pre-calibrated noise model [6], and apply Bayer subsampling as in [7].…”

Section: Reference For Demosaicmentioning

confidence: 99%

“…No For demosaic, reference RGB image and its corresponding Bayer image can be simulated by adding noise on linearized clean RGB image using pre-calibrated noise model [6], and apply Bayer subsampling as in [7].…”

Section: Reference For Demosaicmentioning

confidence: 99%

Automatic ISP Image Quality Tuning Using Nonlinear Optimization

Nishimura¹,

Gerasimow²,

Sushma³

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Fig. 1. Comparison of ISP output images with different tunings on IMX260 ISO400. From left to right: Not-tuned, Hand-tuned by image quality expert, Auto-tuned. ABSTRACTImage Signal Processor (ISP) comprises of various blocks to reconstruct image sensor raw data to final image consumed by human visual system or computer vision applications. Each block typically has many tuning parameters due to the complexity of the operation. These need to be hand tuned by Image Quality (IQ) experts, which takes considerable amount of time. In this paper, we present an automatic IQ tuning using nonlinear optimization and automatic reference generation algorithms. The proposed method can produce high quality IQ in minutes as compared with weeks of handtuned results by IQ experts. In addition, the proposed method can work with any algorithms without being aware of their specific implementation. It was found successful on multiple different processing blocks such as noise reduction, demosaic, and sharpening.

show abstract

Turbo denoising for mobile photographic applications

Cited by 6 publications

References 13 publications

NIMA: Neural Image Assessment

NIMA: Neural Image Assessment

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

Automatic ISP Image Quality Tuning Using Nonlinear Optimization

Contact Info

Product

Resources

About