Semi-supervised correction model for turbulence-distorted images.

Significant progress has been made in addressing turbulence distortion in recent years, but persistent challenges remain. Firstly, existing methods heavily rely on fully supervised optimization strategies and synthetic datasets, posing difficulties in effectively utilizing unlabeled real data for training. Secondly, most approaches construct networks in a straightforward manner, overlooking the representation model of phase distortion and point spread function (PSF) in spatial and channel dimensions. This oversight restricts the potential for distortion correction. To address these challenges, this paper proposes a semi-supervised atmospheric turbulence correction method based on the mean-teacher framework. Our approach imposes constraints on the unlabeled data of student networks using pseudo-labels generated by teacher networks, thereby enhancing the generalization ability by leveraging information from unlabeled data. Furthermore, we introduce to use no-reference image quality assessment criterion to select the most reliable pseudo-label for each unlabeled sample by predicting physical parameters that indicating the level of degradation. Additionally, we propose to combine sliding window-based self-attention with channel attention to facilitate local-global context interaction. This design is inspired by the representation of phase distortion and PSF, which can be characterized by coefficients and basis functions corresponding to the channel-wise representation of convolutional neural network features. Moreover, the base functions exhibit spatial correlation, akin to Zenike and Airy disks. Experimental results show that the proposed method surpasses state-of-the-art models.

TSRRNet: two-stage reflection removal network with reflective guidance.

Due to the shortage of paired images, the training of reflection removal networks relies heavily on synthesized samples, for which the ground truths of transmission and reflection are both known. But most existing CNN-based models cannot fully utilize the reflection information, which may cause performance limitations. In this paper, our goal is to design a novel, to the best of our knowledge, network that can take the reflection layer to refine the transmission layer. To this end, we propose a two-stage generative-adversarial-network-based network, where the first stage is used to obtain the coarse estimation of transmission and reflection, and the second stage is used to achieve the refinement. In addition, instead of just applying two penalty terms on the two coarse predictions in previous works, we consider the coarse reflection as a soft mask overlapped on the transmission and apply the recently proposed gated convolution into the second stage for further refinement. The network is trained with an adversarial frame using WGAN. The experimental results with benchmark datasets indicate that our method outperforms several state-of-the-art networks.

Panchromatic Image Super-Resolution Via Self Attention-Augmented Wasserstein Generative Adversarial Network.

Panchromatic (PAN) images contain abundant spatial information that is useful for earth observation, but always suffer from low-resolution ( LR) due to the sensor limitation and large-scale view field. The current super-resolution (SR) methods based on traditional attention mechanism have shown remarkable advantages but remain imperfect to reconstruct the edge details of SR images. To address this problem, an improved SR model which involves the self-attention augmented Wasserstein generative adversarial network ( SAA-WGAN) is designed to dig out the reference information among multiple features for detail enhancement. We use an encoder-decoder network followed by a fully convolutional network (FCN) as the backbone to extract multi-scale features and reconstruct the High-resolution (HR) results. To exploit the relevance between multi-layer feature maps, we first integrate a convolutional block attention module (CBAM) into each skip-connection of the encoder-decoder subnet, generating weighted maps to enhance both channel-wise and spatial-wise feature representation automatically. Besides, considering that the HR results and LR inputs are highly similar in structure, yet cannot be fully reflected in traditional attention mechanism, we, therefore, designed a self augmented attention (SAA) module, where the attention weights are produced dynamically via a similarity function between hidden features; this design allows the network to flexibly adjust the fraction relevance among multi-layer features and keep the long-range inter information, which is helpful to preserve details. In addition, the pixel-wise loss is combined with perceptual and gradient loss to achieve comprehensive supervision. Experiments on benchmark datasets demonstrate that the proposed method outperforms other SR methods in terms of both objective evaluation and visual effect.