Rethinking Noise Synthesis and Modeling in Raw Denoising
- URL: http://arxiv.org/abs/2110.04756v1
- Date: Sun, 10 Oct 2021 10:45:24 GMT
- Title: Rethinking Noise Synthesis and Modeling in Raw Denoising
- Authors: Yi Zhang, Hongwei Qin, Xiaogang Wang, Hongsheng Li
- Abstract summary: We introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise.
It inherently generates accurate raw image noise for different camera sensors.
- Score: 75.55136662685341
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The lack of large-scale real raw image denoising dataset gives rise to
challenges on synthesizing realistic raw image noise for training denoising
models. However, the real raw image noise is contributed by many noise sources
and varies greatly among different sensors. Existing methods are unable to
model all noise sources accurately, and building a noise model for each sensor
is also laborious. In this paper, we introduce a new perspective to synthesize
noise by directly sampling from the sensor's real noise. It inherently
generates accurate raw image noise for different camera sensors. Two efficient
and generic techniques: pattern-aligned patch sampling and high-bit
reconstruction help accurate synthesis of spatial-correlated noise and high-bit
noise respectively. We conduct systematic experiments on SIDD and ELD datasets.
The results show that (1) our method outperforms existing methods and
demonstrates wide generalization on different sensors and lighting conditions.
(2) Recent conclusions derived from DNN-based noise modeling methods are
actually based on inaccurate noise parameters. The DNN-based methods still
cannot outperform physics-based statistical methods.
Related papers
- Physics-guided Noise Neural Proxy for Practical Low-light Raw Image
Denoising [22.11250276261829]
Recently, the mainstream practice for training low-light raw image denoising has shifted towards employing synthetic data.
Noise modeling, which focuses on characterizing the noise distribution of real-world sensors, profoundly influences the effectiveness and practicality of synthetic data.
We propose a novel strategy: learning the noise model from dark frames instead of paired real data, to break down the data dependency.
arXiv Detail & Related papers (2023-10-13T14:14:43Z) - Towards General Low-Light Raw Noise Synthesis and Modeling [37.87312467017369]
We introduce a new perspective to synthesize the signal-independent noise by a generative model.
Specifically, we synthesize the signal-dependent and signal-independent noise in a physics- and learning-based manner.
In this way, our method can be considered as a general model, that is, it can simultaneously learn different noise characteristics for different ISO levels.
arXiv Detail & Related papers (2023-07-31T09:10:10Z) - Realistic Noise Synthesis with Diffusion Models [68.48859665320828]
Deep image denoising models often rely on large amount of training data for the high quality performance.
We propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD)
RNSD can incorporate guided multiscale content, such as more realistic noise with spatial correlations can be generated at multiple frequencies.
arXiv Detail & Related papers (2023-05-23T12:56:01Z) - Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images [35.29066692454865]
This paper proposes a framework for training a noise model and a denoiser simultaneously.
It relies on pairs of noisy images rather than noisy/clean paired image data.
The trained denoiser is shown to significantly improve upon both supervised and weakly supervised baseline denoising approaches.
arXiv Detail & Related papers (2022-06-02T15:31:40Z) - Estimating Fine-Grained Noise Model via Contrastive Learning [11.626812663592416]
We propose an innovative noise model estimation and noise synthesis pipeline for realistic noisy image generation.
Our model learns a noise estimation model with fine-grained statistical noise model in a contrastive manner.
By calibrating noise models of several sensors, our model can be extended to predict other cameras.
arXiv Detail & Related papers (2022-04-03T02:35:01Z) - C2N: Practical Generative Noise Modeling for Real-World Denoising [53.96391787869974]
We introduce a Clean-to-Noisy image generation framework, namely C2N, to imitate complex real-world noise without using paired examples.
We construct the noise generator in C2N accordingly with each component of real-world noise characteristics to express a wide range of noise accurately.
arXiv Detail & Related papers (2022-02-19T05:53:46Z) - IDR: Self-Supervised Image Denoising via Iterative Data Refinement [66.5510583957863]
We present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance.
Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising.
To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes.
arXiv Detail & Related papers (2021-11-29T07:22:53Z) - Physics-based Noise Modeling for Extreme Low-light Photography [63.65570751728917]
We study the noise statistics in the imaging pipeline of CMOS photosensors.
We formulate a comprehensive noise model that can accurately characterize the real noise structures.
Our noise model can be used to synthesize realistic training data for learning-based low-light denoising algorithms.
arXiv Detail & Related papers (2021-08-04T16:36:29Z) - Adaptive noise imitation for image denoising [58.21456707617451]
We develop a new textbfadaptive noise imitation (ADANI) algorithm that can synthesize noisy data from naturally noisy images.
To produce realistic noise, a noise generator takes unpaired noisy/clean images as input, where the noisy image is a guide for noise generation.
Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
arXiv Detail & Related papers (2020-11-30T02:49:36Z) - Learning Camera-Aware Noise Models [22.114167097784787]
We propose a data-driven approach, where a generative noise model is learned from real-world noise.
The proposed noise model is camera-aware, that is, different noise characteristics of different camera sensors can be learned simultaneously.
arXiv Detail & Related papers (2020-08-21T08:25:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.