HighEr-Resolution Network for Image Demosaicing and Enhancing

Mei, Kangfu; Li, Juncheng; Zhang, Jiajie; Wu, Haoyu; Li, Jie; Huang, Rui

doi:10.1109/iccvw.2019.00427

Cited by 24 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our CBUnet with previous learnt approaches like PyNET [21], HERN [26] and AWNet [10]. As shown in Table 2, we list the reconstruction PSNR (averaged), parameters and floating-point operation (FLOPs).…”

Section: Resultsmentioning

confidence: 99%

Rendering Nighttime Image Via Cascaded Color and Brightness Compensation

Li¹,

Yi²,

Ma³

2022

Preprint

View full text Add to dashboard Cite

Image signal processing (ISP) is crucial for camera imaging, and neural networks (NN) solutions are extensively deployed for daytime scenes. The lack of sufficient nighttime image dataset and insights on nighttime illumination characteristics poses a great challenge for high-quality rendering using existing NN ISPs. To tackle it, we first built a high-resolution nighttime RAW-RGB (NR2R) dataset with white balance and tone mapping annotated by expert professionals. Meanwhile, to best capture the characteristics of nighttime illumination light sources, we develop the CBUnet, a two-stage NN ISP to cascade the compensation of color and brightness attributes. Experiments show that our method has better visual quality compared to traditional ISP pipeline, and is ranked at the second place in the NTIRE 2022 Night Photography Rendering Challenge [13] for two tracks by respective People's and Professional Photographer's choices. The code and relevant materials are avaiable on our website 1 .

show abstract

Section: Resultsmentioning

confidence: 99%

Rendering Nighttime Image Via Cascaded Color and Brightness Compensation

Li¹,

Yi²,

Ma³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Unlike with other image restoration tasks, such as image denoising [ 12 , 13 , 14 ], image dehazing [ 15 , 16 ], and image demosaicing [ 17 , 18 ], the difficulty of image demoiréing is how to remove moiré patterns with various frequencies and color distortion. With the widespread popularity of deep learning, deep convolutional neural networks have also been applied to image demoiréing.…”

Section: Related Workmentioning

confidence: 99%

Learning Moiré Pattern Elimination in Both Frequency and Spatial Domains for Image Demoiréing

Liu

Wang

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Recently, with the rapid development of mobile sensing technology, capturing scene information by mobile sensing devices in the form of images or videos has become a prevalent recording method. However, the moiré pattern phenomenon may occur when the scene contains digital screens or regular strips, which greatly degrade the visual performance and image quality. In this paper, considering the complexity and diversity of moiré patterns, we propose a novel end-to-end image demoiré method, which can learn moiré pattern elimination in both the frequency and spatial domains. To be specific, in the frequency domain, considering the signal energy of moiré pattern is widely distributed in the frequency, we introduce a wavelet transform to decompose the multi-scale image features, which can help the model identify the moiré features more precisely to suppress them effectively. On the other hand, we also design a spatial domain demoiré block (SDDB). The SDDB module can extract moiré features from the mixed features, then subtract them to obtain clean image features. The combination of the frequency domain and the spatial domain enhances the model’s ability in terms of moiré feature recognition and elimination. Finally, extensive experiments demonstrate the superior performance of our proposed method to other state-of-the-art methods. The Grad-CAM results in our ablation study fully indicate the effectiveness of the two proposed blocks in our method.

show abstract

“…For example, [31] considers using the stacked U-Nets to produce a pipeline in a coarse-to-fine manner. [23] adopts a multi-scale training strategy that recovers the image details while remaining the global perceptual acceptance. The most recent work [13] tries to narrow the visual quality gap between the mobile and DSLR color images by directly translating mobile RAW images to DSLR color ones, where RAW images are captured by Huawei P20 phone and color ones are from Canon 5D Mark IV.…”

Section: Deep Learning Based Image Isp Pipelinementioning

confidence: 99%

AWNet: Attentive Wavelet Network for Image ISP

Dai¹,

Xiao-hong²,

Li³

2020

Preprint

View full text Add to dashboard Cite

As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of camera sensors on phone, the photographed image is still visually distinct to the one taken by the digital single-lens reflex (DSLR) camera. To narrow this performance gap, one is to redesign the camera image signal processor (ISP) to improve the image quality. Owing to the rapid rise of deep learning, recent works resort to the deep convolutional neural network (CNN) to develop a sophisticated data-driven ISP that directly maps the phone-captured image to the DSLR-captured one. In this paper, we introduce a novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem. By adding the wavelet transform, our proposed method enables us to restore favorable image details from RAW information and achieve a larger receptive field while remaining high efficiency in terms of computational cost. The global context block is adopted in our method to learn the non-local color mapping for the generation of appealing RGB images. More importantly, this block alleviates the influence of image misalignment occurred on the provided dataset. Experimental results indicate the advances of our design in both qualitative and quantitative measurements.

show abstract

HighEr-Resolution Network for Image Demosaicing and Enhancing

Cited by 24 publications

References 17 publications

Rendering Nighttime Image Via Cascaded Color and Brightness Compensation

Rendering Nighttime Image Via Cascaded Color and Brightness Compensation

Learning Moiré Pattern Elimination in Both Frequency and Spatial Domains for Image Demoiréing

AWNet: Attentive Wavelet Network for Image ISP

Contact Info

Product

Resources

About