Imaging systems often produce underexposed or overexposed images due to their limited capacity to capture the full range of natural illumination. To address this limitation, deep high dynamic range (HDR) imaging methods rely on fusing multiple low dynamic range (LDR) images, demonstrating remarkable performance in recent years. However, most existing methods solely focus on object motions, disregarding real-world noise in images, which typically leads to suboptimal solutions in actual situations. In this paper, we propose a dynamic spatial aggregation network, which can simultaneously handle noise and large motion of objects in LDR images in real-world scenarios. Our method employs a dynamic convolutional operator, which is image-specific and ensures robustness to noise and misaligned image content, to adaptively extract features from input LDR images. Experimental results demonstrate that our proposed method significantly outperforms state-of-the-art deep HDR models, resulting in high-quality HDR images in real-world situations.
KEYWORDS: High dynamic range imaging, Image processing, Performance modeling, Visualization, Time multiplexed optical shutter, Visual process modeling, Image compression, Range imaging, Image quality, Feature extraction
Modern digital cameras typically cannot capture the whole range of illumination, due to the limited sensing capability of sensor devices. High dynamic range (HDR) imaging aims to generate images with a larger range of illumination by merging multiple low-dynamic range (LDR) images with different exposure times. However, when the images are captured in dynamic scenes, existing methods unavoidably produce undesirable artifacts and distorted content. In this paper, we propose a multi-level feature aggregation network, based on the Laplacian pyramid, to address this issue for HDR imaging. The proposed method progressively aggregates non-overlapping frequency sub-bands at different pyramid levels, and generates the corresponding HDR image from coarser to finer scales. Experiment results show that our proposed method can significantly outperform other competitive HDR methods, thereby producing HDR images with high visual quality.
Sparse models have been widely used in image denoising, and have achieved state-of-the-art performance in past years. Dictionary learning and sparse code estimation are the two key issues for sparse models. When a dictionary is learned, sparse code estimation is equivalent to a general least absolute shrinkage and selection operator (LASSO) problem. However, there are two limitations of LASSO: 1). LASSO gives rise to a biased estimation. 2). LASSO cannot select highly correlated features simultaneously. In recent years, methods for dictionary construction based on the nonlocal self-similarity property and weighted sparse model, relying on noise estimation, have been proposed. These methods can reduce the biased gap of the estimation, and thus achieve promising results for image denoising. In this paper, we propose an elastic net with adaptive weight for image denoising. Our proposed model can achieve nearly unbiased estimation and select highly correlated features. Experimental results show that our proposed method outperforms other state-of-the-art image denoising methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.