However, the quality of synthetic data is inherently limited by the low accuracy of the noise model, which decreases the performance of low-light raw image denoising.
Recently, the transformation of standard dynamic range TV (SDRTV) to high dynamic range TV (HDRTV) is in high demand due to the scarcity of HDRTV content.
In this paper, we introduce a new perspective to handle various diffraction in UDC images by jointly exploring the feature restoration in the frequency and spatial domains, and present a Frequency and Spatial Interactive Learning Network (FSI).
Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream.
Ranked #1 on Image Denoising on SID SonyA7S2 x100
In particular, we take well-trained CBDNet, NBNet, HINet, Uformer and GMSNet into denoiser pool, and a U-Net is adopted to predict pixel-wise weighting maps to fuse these denoisers.
Subsequently, image denosing can be achieved by selecting corresponding basis of the signal subspace and projecting the input into such space.
Ranked #1 on Image Denoising on SIDD (SSIM (sRGB) metric)
Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets.
In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image denoising.
Overall, our method improves the prediction accuracies of QNNs without introducing extra computation during inference, has negligible impact on training speed, and is applicable to both Convolutional Neural Networks and Recurrent Neural Networks.
Temporal drift of sensory data is a severe problem impacting the data quality of wireless sensor networks (WSNs).
Previous approaches for scene text detection have already achieved promising performances across various benchmarks.
Ranked #3 on Scene Text Detection on COCO-Text