We propose Diff-Shadow, a global-guided diffusion model for high-quality shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but they are not exempt from issues related to inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to realize shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextual information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on three publicly standard datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the ISTD dataset.

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges. By encoding camera settings into a time-aware camera-conditioned affine modulation (TCCAM), RNSD generates more realistic noise distributions under various camera conditions. Additionally, RNSD integrates a multi-scale content-aware module (MCAM), enabling the generation of structured noise with spatial correlations across multiple frequencies. We also introduce Deep Image Prior Sampling (DIPS), a learnable sampling sequence based on depth image prior, which significantly accelerates the sampling process while maintaining the high quality of synthesized noise. Extensive experiments demonstrate that our RNSD method significantly outperforms existing techniques in synthesizing realistic noise under multiple metrics and improving image denoising performance.

Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the complex calculation of multi-head self-attention (MSA), seriously hindering their practical application and deployment. In this work, we present an efficient SR model to mitigate the dilemma between model efficiency and SR performance, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA). From the perspective of information theory, EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. On the other hand, SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features. Since the implementation of EA and SLKA does not involve complex computations (such as extensive matrix multiplications), the proposed method can achieve faster nonlinear inference than Transformer-based SR models while maintaining better SR performance. Extensive experiments show that the proposed model can significantly reduce the delay of model inference while achieving the SR performance comparable with other advanced models.

In this paper, we introduce a new approach for high-quality multi-exposure image fusion (MEF). We show that the fusion weights of an exposure can be encoded into a 1D lookup table (LUT), which takes pixel intensity value as input and produces fusion weight as output. We learn one 1D LUT for each exposure, then all the pixels from different exposures can query 1D LUT of that exposure independently for high-quality and efficient fusion. Specifically, to learn these 1D LUTs, we involve attention mechanism in various dimensions including frame, channel and spatial ones into the MEF task so as to bring us significant quality improvement over the state-of-the-art (SOTA). In addition, we collect a new MEF dataset consisting of 960 samples, 155 of which are manually tuned by professionals as ground-truth for evaluation. Our network is trained by this dataset in an unsupervised manner. Extensive experiments are conducted to demonstrate the effectiveness of all the newly proposed components, and results show that our approach outperforms the SOTA in our and another representative dataset SICE, both qualitatively and quantitatively. Moreover, our 1D LUT approach takes less than 4ms to run a 4K image on a PC GPU. Given its high quality, efficiency and robustness, our method has been shipped into millions of Android mobiles across multiple brands world-wide. Code is available at: https://github.com/Hedlen/MEFLUT.

In recent years, deep convolutional neural networks (DCNNs) have been widely used in the task of ship target detection in synthetic aperture radar (SAR) imagery. However, the vast storage and computational cost of DCNN limits its application to spaceborne or airborne onboard devices with limited resources. In this paper, a set of lightweight detection networks for SAR ship target detection are proposed. To obtain these lightweight networks, this paper designs a network structure optimization algorithm based on the multi-objective firefly algorithm (termed NOFA). In our design, the NOFA algorithm encodes the filters of a well-performing ship target detection network into a list of probabilities, which will determine whether the lightweight network will inherit the corresponding filter structure and parameters. After that, the multi-objective firefly optimization algorithm (MFA) continuously optimizes the probability list and finally outputs a set of lightweight network encodings that can meet the different needs of the trade-off between detection network precision and size. Finally, the network pruning technology transforms the encoding that meets the task requirements into a lightweight ship target detection network. The experiments on SSDD and SDCD datasets prove that the method proposed in this paper can provide more flexible and lighter detection networks than traditional detection networks.

The huge computing and storage requirements of deep con-volutional neural networks (DCNNs) limit their application on edge computing devices. In this article, we propose an attention mechanism based on the feature map quality evaluation algorithm (IQE). The knowledge distillation method based on the IQE attention mechanism uses the IQE method to identify important knowledge in the pre-trained SAR target recognition deep neural network. Then in the process of knowledge distillation, the lightweight network is forced to focus on the learning of important knowledge. Through this mechanism, the method proposed in this paper can efficiently transfer the knowledge of the pre-trained SAR target recognition network to the lightweight network, which makes it is possible to deploy the SAR target recognition algorithm on the edge computing platform. Comparison experiments with several commonly used knowledge distillation methods have proved the effectiveness of our proposed method. In addition, we also verified the performance of the lightweight network obtained by our method on the edge platform based on the K210 processor.

In this paper, a novel multi-task sparse representation (MSR) of the monogenic signal is proposed in order to overcome the misclassification caused by heterogeneity of three components of the monogenic signal. In recent years, the monogenic signal has been applied into the field of SAR image recognition due to its capability of capturing the broad spectral information with maximal spatial localization. The monogenic signal can be decomposed into three components (local amplitude, local phase and local orientation) at different scales. The components are concatenated to three component-specific features and then fed into a MSR classification framework. However, the heterogeneity of the three component-specific features makes it difficult to make decisions by simply counting the accumulated error in multi-task sparse representation classification. To solve this problem, a multi-task learning model based on Fisher discrimination criteria is designed and Fisher score is presented to measure the discriminative ability of three types of component-specific feature in different classes. The final decision is made by weighted accumulated reconstruction error. Experiment results prove the effectiveness of adaptive weighted MSR classification method of monogenic signal.

Deep Convolutional Neural Networks (DCNNs) have been widely used in target recognition due to the availability of large dataset. The DCNNs have the ability of learning highly hierarchical image feature, which provides great opportunity for synthetic aperture radar automatic target recognition (SAR-ATR). However, when the DCNNs were directly applied to the SAR target recognition, it will result in severe overfitting due to limited SAR image training data. To overcome this problem, we present a Gabor-Deep Convolutional Neural Networks (G-DCNNs). Instead of training a deep network with limited dataset of raw SAR images, Gabor features for multi -scale and multi -direction were used for data augmentation as training dataset at first. Then based on this data augmentation method, we designed a DCNNs for SAR image target recognition. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset prove the effectiveness of our method.