Learning Raw Image Denoising With Bayer Pattern Unification and Bayer Preserving Augmentation

@article{Liu2019LearningRI,
  title={Learning Raw Image Denoising With Bayer Pattern Unification and Bayer Preserving Augmentation},
  author={Jiaming Liu and Chihao Wu and Yuzhi Wang and Qin Xu and Yuqian Zhou and Haibin Huang and Chuan Wang and Shaofan Cai and Yifan Ding and Haoqiang Fan and Jue Wang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2019},
  pages={2070-2077}
}
  • Jiaming Liu, Chihao Wu, Jue Wang
  • Published 29 April 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image denoising. Compared with traditional RGB image denoising, performing this task on direct camera sensor readings presents new challenges such as how to effectively handle various Bayer patterns from different data sources, and subsequently how to perform valid data augmentation with raw images. To address the first problem, we propose a Bayer pattern unification (BayerUnify) method to unify… 

Figures and Tables from this paper

CycleISP: Real Image Restoration via Improved Data Synthesis
TLDR
This paper presents a framework that models camera imaging pipeline in forward and reverse directions that allows any number of realistic image pairs for denoising both in RAW and sRGB spaces and achieves the state-of-the-art performance on real camera benchmark datasets.
Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
TLDR
This paper proposes and study Wild-JDD, a novel learning framework for joint demosaicking and denoising in the wild taking into account ground truth uncertainty, which outperforms state-of-the-art schemes on joint dem Rosaicking and Denoising tasks on both synthetic and realistic raw datasets.
Real Image Denoising Based on Multi-Scale Residual Dense Block and Cascaded U-Net with Block-Connection
TLDR
Two new networks are introduced, which are multi- scale residual dense network (MRDN) and multi-scale residual dense cascaded U-Net with block-connection (MCU-Net), built upon a newly designed multi- Scale residual dense block (MRDB).
Practical Deep Raw Image Denoising on Mobile Devices
TLDR
This work proposes a light-weight, efficient neural network-based raw image denoiser that runs smoothly on mainstream mobile devices, and produces high quality denoising results.
Supervised Raw Video Denoising With a Benchmark Dataset on Dynamic Scenes
TLDR
This paper creates motions for controllable objects, such as toys, and captures each static moment for multiple times to generate clean video frames, resulting in the first dynamic video dataset with noisy-clean pairs.
Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS
TLDR
A deformable kernel prediction neural network (DKPNN) is proposed for joint denoising and motion artifact removal, and a data generation method which generates images with color-channel motion artifacts is also proposed to train the DKPNN.
In-Camera Raw Compression: A New Paradigm from Image Acquisition to Display
TLDR
The NeuralCAM is proposed- a new camera processing paradigm where the sensor raw Bayer data is compressed and the image signal processor is applied at users’ client for on-demand rendering and processing.
DeepSelfie: Single-Shot Low-Light Enhancement for Selfies
TLDR
Through extensive experiments of no-reference image quality assessment as well as human subjective evaluation, it is shown that DeepSelfie provides better results in comparison to several state-of-the-art methods.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
TLDR
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results, based on the SIDD benchmark.
NTIRE 2019 Challenge on Real Image Denoising: Methods and Results
  • A. Abdelhamed, R. Timofte, Z. Cao
  • Engineering
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2019
TLDR
The proposed methods by the 15 teams represent the current state-of-the-art performance in image denoising targeting real noisy images.
...
1
2
3
...

References

SHOWING 1-10 OF 36 REFERENCES
Deep joint demosaicking and denoising
TLDR
A new data-driven approach forDemosaicking and denoising is introduced: a deep neural network is trained on a large corpus of images instead of using hand-tuned filters and this network and training procedure outperform state-of-the-art both on noisy and noise-free data.
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance.
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising
TLDR
The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance, and enjoys several desirable properties, including the ability to handle a wide range of noise levels effectively with a single network.
Image Denoising and Inpainting with Deep Neural Networks
TLDR
A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random.
Deep Image Prior
TLDR
It is shown that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, superresolution, and inpainting.
Non-local sparse models for image restoration
TLDR
Experimental results in image denoising and demosaicking tasks with synthetic and real noise show that the proposed method outperforms the state of the art, making it possible to effectively restore raw images from digital cameras at a reasonable speed and memory cost.
Learning to See in the Dark
TLDR
A pipeline for processing low-light images is developed, based on end-to-end training of a fully-convolutional network that operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data.
Joint demosaicing and denoising
TLDR
The experimental results confirm that the proposed method suppresses noise (CMOS/CCD image sensor noise model) while effectively interpolating the missing pixel components, demonstrating a significant improvement in image quality when compared to treating demosaicing and denoising problems independently.
RENOIR - A dataset for real low-light image noise reduction
Natural Image Denoising with Convolutional Networks
TLDR
An approach to low-level vision is presented that combines the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models to avoid computational difficulties in MRF approaches that arise from probabilistic learning and inference.
...
1
2
3
4
...