While thermal imaging technology on unmanned aerial vehicles (UAVs) has made significant progress, the widespread issue of insufficient resolution poses a serious challenge to comprehending the content of thermal images. Moreover, deploying super-resolution models on resource-limited UAVs presents considerable difficulties. In an effort to address these challenges, we propose a lightweight thermal image super-resolution (LTSR) model that efficiently extracts multi-scale features and learns latent representations. First, we construct a multi-scale knowledge distillation (MSKD) network to extract discriminative features from low-resolution inputs. To achieve this, we employ convolution with varying dilation rates to extract features from diverse receptive fields and compress these features through knowledge distillation. Second, to effectively establish continuous relationships among features in the latent space, we develop a forward Markovian restoration process involving multiple diffusion iterations. In each iteration, we integrate the lightweight MSKD network and latent neural representation into a unified end-to-end framework. When evaluated on the challenging benchmark dataset, our method not only has fewer parameters but also outperforms state-of-the-art methods in super-resolution accuracy. Extensive ablation analysis validates the effectiveness of each component in our LTSR.

Weakly supervised semantic segmentation (WSSS) has received considerable interest since it relies only on image-level annotations rather than fine-grained pixel-wise annotations, which require vast human labor. Generating pseudo-masks (a.k.a. seeds) is arguably the most standard step for WSSS. The main difficulty is that seeds are usually sparse and incomplete. In this paper, we propose a dual branch framework by positive and negative learning for WSSS, which distills more accurate semantic information from multiple seeds instead of struggling to refine a single seed. First, we integrate different classification networks with class activation maps to generate multiple seeds. Then, considering that richer information exists in different seeds, we perform multi-source information distillation to obtain aggregated seeds that include clean labels and noisy labels, which are more comprehensive and reliable to train a segmentation model. Furthermore, we construct a dual branch segmentation network, which makes full use of correct information while eliminating incorrect information from distilled seeds that are further acquired by aggregated seeds. When evaluated on two benchmark datasets, our method outperforms state-of-the-art methods, demonstrating the superior performance.

High-resolution (HR) medical images provide clearer anatomical details and facilitate early disease diagnosis, yet acquiring HR scans is often limited by imaging conditions, device capabilities, and patient factors. We propose a transform domain deep multiscale feature fusion generative adversarial network (MSFF-GAN) for medical image super-resolution (SR). Considering the advantages of generative adversarial networks (GANs) and convolutional neural networks (CNNs), MSFF-GAN integrates a deep multi-scale convolution network into the GAN generator, which is composed primarily of a series of cascaded multi-scale feature extraction blocks in a coarse-to-fine manner to restore the medical images. Two tailored blocks are designed: a multiscale information distillation (MSID) block that adaptively captures long- and short-path features across scales, and a granular multiscale (GMS) block that expands receptive fields at fine granularity to strengthen multiscale feature extraction with reduced computational cost. Unlike conventional methods that predict HR images directly in the spatial domain, which often yield excessively smoothed outputs with missing textures, we formulate SR as the prediction of coefficients in the non-subsampled shearlet transform (NSST) domain. This transform domain modeling enables better preservation of global anatomical structure and local texture details. The predicted coefficients are inverted to reconstruct HR images, and the transform domain subbands are also fed to the discriminator to enhance its discrimination ability and improve perceptual fidelity. Extensive experiments on medical image datasets demonstrate that MSFF-GAN outperforms state-of-the-art approaches in structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), while more effectively preserving global anatomy and fine textures. These results validate the effectiveness of combining multiscale feature fusion with transform domain prediction for high-quality medical image super-resolution.

Ineffective recognition of weak seismic signals limits fine structural interpretation and reservoir prediction in seismic exploration. Although seismic signal reconstruction has made significant progress, the widespread issue of low Signal-to-Noise Ratio (SNR) remains a major challenge in recovering weak seismic signals from noisy field data. To address this, we propose a prior-based Latent denoising Diffusion model for weak Seismic signal Restoration (LDSR). First, we design a Multi-Scale Information Distillation Attention (MSIDA) network to extract discriminative features from noisy inputs and aggregate the multi-scale spatial information, ensuring more stable model convergence. Second, to effectively establish continuous relationships among features in the latent space, we develop a forward Markovian restoration process involving multiple diffusion iterations. In each iteration, we integrate the MSIDA network and latent neural representation into a unified end-to-end framework. Third, we leverage Non-Subsampled Shearlet Transform (NSST) sub-bands to represent high-frequency prior, which is expected to enhance the details of reconstructed seismic signals. When evaluated on synthetic and logging forward data, our method outperforms state-of-the-art methods. Ablation studies validate the effectiveness of each component in LDSR. When processed on real field data, LDSR successfully restores more effective weak signals near the target layers.