Noise Characteristics and Noise Perception

Seybold, Tamara

doi:10.1007/978-3-319-96029-6_9

Cited by 2 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this approach does not match the real noise distribution. As discussed in [27], noise in raw images can be approximated with a Poissonian distribution. This noise distribution is transformed by the camera image processing pipeline, which renders the resulting distribution signal-dependant and correlated among neighboring pixels [28].…”

Section: Problem Formulationmentioning

confidence: 99%

Bridging the Domain Gap in Real World Super-Resolution

Laroche¹,

Tassano²

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper, we propose a state-of-the-art super-resolution algorithm and a framework to effectively train this architecture to handle real-world images. Recent learning-based, super-resolution methods have achieved impressive performance on ideal datasets. However, their performance plummets when tested on real images, as their assumed degradation model deviates from reality. Instead of assuming simplistic degradations, we make use of generative methods to mimic real degradations in order to narrow the domain gap between training data and testing data. In particular, we employ a novel Normalizing Flow architecture to replicate realistic noise and camera pipeline degradations. This framework, in conjunction with a carefully designed neural network architecture, results in a superresolution algorithm which compares favorably to other methods. As for the model architecture, the combination between its performance on real images and lower computational load makes it attractive for practical super-resolution applications. We compare our method with different state-of-art algorithms, both on synthetic and real images. The experimental results demonstrate the remarkable performance of our super-resolution algorithm in real-world applications.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Bridging the Domain Gap in Real World Super-Resolution

Laroche¹,

Tassano²

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…For video denoising algorithms, temporal coherence and the lack of flickering are crucial aspects in the perceived quality of the results [24], [25]. In order to achieve these, an algorithm must make use of the temporal information existent in neighboring frames when denoising a given frame of an image sequence.…”

Section: Fastdvdnetmentioning

confidence: 99%

FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation

Tassano¹,

Delon²,

Veit³

2019

Preprint

View full text Add to dashboard Cite

In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture. Until recently, video denoising with neural networks had been a largely under explored domain, and existing methods could not compete with the performance of the best patchbased methods. The approach we introduce in this paper, called FastDVDnet, shows similar or better performance than other state-of-the-art competitors with significantly lower computing times. In contrast to other existing neural network denoisers, our algorithm exhibits several desirable properties such as fast runtimes, and the ability to handle a wide range of noise levels with a single network model. The characteristics of its architecture make it possible to avoid using a costly motion compensation stage while achieving excellent performance. The combination between its denoising performance and lower computational load makes this algorithm attractive for practical denoising applications. We compare our method with different state-of-art algorithms, both visually and with respect to objective quality metrics.

show abstract

Noise Characteristics and Noise Perception

Cited by 2 publications

References 50 publications

Bridging the Domain Gap in Real World Super-Resolution

Bridging the Domain Gap in Real World Super-Resolution

FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation

Contact Info

Product

Resources

About