Blind Super-Resolution (blind SR) aims to enhance the model’s generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by regularizing features, have shown promising results in blind SR. Nevertheless, these methods focus solely on regularizing features before the final layer and overlook the need for generalization in features at intermediate layers. Without explicit regularization of features at intermediate layers, the blind SR network struggles to obtain well-generalized feature representations. However, the key challenge is that directly applying dropout to intermediate layers leads to a significant performance drop, which we attribute to the inconsistency in training-testing and across layers it introduced. Therefore, we propose Adaptive Dropout, a new regularization method for blind SR models, which mitigates the inconsistency and facilitates application across intermediate layers of networks. Specifically, for training-testing inconsistency, we re-design the form of dropout and integrate the features before and after dropout adaptively. For inconsistency in generalization requirements across different layers, we innovatively design an adaptive training strategy to strengthen feature propagation by layer-wise annealing. Experimental results show that our method outperforms all past regularization methods on both synthetic and real-world benchmark datasets, also highly effective in other image restoration tasks. Code is available at https://github.com/xuhang07/Adpative-Dropout.

Diffusion models have demonstrated remarkable success in generative tasks, yet their iterative denoising process results in slow inference, limiting their practicality. While existing acceleration methods exploit the well-known U-shaped similarity pattern between adjacent steps through caching mechanisms, they lack theoretical foundation and rely on simplistic computation reuse, often leading to performance degradation. In this work, we provide a theoretical understanding by analyzing the denoising process through the second-order Adams-Bashforth method, revealing a linear relationship between the outputs of consecutive steps. This analysis explains why the outputs of adjacent steps exhibit a U-shaped pattern. Furthermore, extending Adams-Bashforth method to higher order, we propose a novel caching-based acceleration approach for diffusion models, instead of directly reusing cached results, with a truncation error bound of only (O(hk) where h is the step size. Extensive validation across diverse image and video diffusion models (including HunyuanVideo and FLUX.1-dev) with various schedulers demonstrates our method's effectiveness in achieving nearly 3× speedup while maintaining original performance levels, offering a practical real-time solution without compromising generation quality.

Vertically transverse isotropic (VTI) media are widely present in the Earth's crust, particularly in reservoirs; therefore, accurately characterizing crustal stratigraphic features is essential. However, most existing inversion methods for VTI media are primarily based on approximate reflection coefficients, with some employing exact coefficient equations, often using two-step strategy or single P-wave inversion. While joint simultaneous inversion based on the exact reflection coefficient equation can yield more accurate results, the increased parameters exacerbate the ill-posed inversion, complicating the process further. To address these challenges, we propose an Amplitude Versus Offset (AVO) Bayesian inversion method for PP- and PS-waves based on the exact reflection coefficient equation of VTI media to invert P- and S-wave velocities, density, and the two anisotropy parameters simultaneously. First, we constructed the inversion objective function within the Bayesian framework and employed the Gauss–Newton method to overcome the local extremum problem and update the model. Our algorithm demonstrated rapid and stable convergence under both ideal and noisy conditions. Notably, our method produced results that were consistent with the well-log data and the actual reservoir, validating its reliability.

Imaging using S-wave seismic data based on elastic media holds the potential to address certain critical issues that conventional P-wave imaging cannot resolve, thereby offering new opportunities for oil and gas exploration. In this article, we have developed a feasible S-wave reverse time migration (RTM) imaging technique. Based on nonconversion elastic wave theory, we introduce auxiliary variables to construct a first-order pure S-wave equation, which is used to simulate the extrapolation of source wavefields in S-wave RTM. In addition, we employ the first-order velocity-stress equation for backward propagation and use decoupled elastic operators for decoupling of receiver wavefields, and utilize vector cross-correlation imaging conditions to obtain scalar imaging results. Compared with traditional P-wave RTM, the proposed S-wave RTM in this article addresses the limitations of traditional P-wave RTM in processing S-wave seismic data, demonstrating its advantages in reacting to reservoir fluid in the field of oil and gas exploration.

Images corrupted by rain streaks often lose vital frequency information for perception, and image deraining aims to solve this problem, which relies on global and local degradation modeling. Recent studies have witnessed the effectiveness and efficiency of Mamba for perceiving global and local information based on its exploiting local correlation among patches, however, rarely attempts have been explored to extend it with frequency analysis for image deraining, limiting its ability to perceive global degradation that is relevant to frequency modeling (e.g. Fourier transform). In this paper, we propose FreqMamba, an effective and efficient paradigm that leverages the complementary between Mamba and frequency analysis for image deraining. The core of our method lies in extending Mamba with frequency analysis from two perspectives: extending it with frequency band for exploiting frequency correlation, and connecting it with Fourier transform for global degradation modeling. Specifically, FreqMamba introduces complementary triple interaction structures including spatial Mamba, frequency-band Mamba, and Fourier global modeling. Frequency-Band Mamba decomposes the image into sub-bands of different frequencies to allow 2D scanning from the frequency dimension. Furthermore, leveraging Mamba's unique data-dependent properties, we use rainy images at different scales to provide degradation priors to the network, thereby facilitating efficient training. Extensive experiments show that our method outperforms state-of-the-art methods both visually and quantitatively. Our code is available at: https://github.com/aSleepyTree/FreqMamba.