The goal of infrared and visible image fusion (TVIF) is to integrate the unique advantages of both modalities to achieve a more comprehensive understanding of a scene. However, existing methods struggle to effectively handle modal disparities, resulting in visual degradation of the details and prominent targets of the fused images. To address these challenges, we introduce PromptFusion, a prompt-based approach that harmoniously combines multi-modality images under the guidance of semantic prompts. Firstly, to better characterize the features of different modalities, a contourlet autoencoder is designed to separate and extract the high-/low-frequency components of different modalities, thereby improving the extraction of fine details and textures. We also introduce a prompt learning mechanism using positive and negative prompts, leveraging Vision-Language Models to improve the fusion model's understanding and identification of targets in multi-modality images, leading to improved performance in downstream tasks. Furthermore, we employ bi-level asymptotic convergence optimization. This approach simplifies the intricate non-singleton non-convex bi-level problem into a series of convergent and differentiable single optimization problems that can be effectively resolved through gradient descent. Our approach advances the state-of-the-art, delivering superior fusion quality and boosting the performance of related downstream tasks. Project page: https://github.com/hey-it-s-me/Prompt-Fusion.

Existing unsupervised monocular depth estimation methods resort to stereo image pairs instead of ground-truth depth maps as supervision to predict scene depth. Constrained by the type of monocular input in testing phase, they fail to fully exploit the stereo information through the network during training, leading to the unsatisfactory performance of depth estimation. Therefore, we propose a novel architecture which consists of a monocular network (Mono-Net) that infers depth maps from monocular inputs, and a stereo network (Stereo-Net) that further excavates the stereo information by taking stereo pairs as input. During training, the sophisticated Stereo-Net guides the learning of Mono-Net and devotes to enhance the performance of Mono-Net without changing its network structure and increasing its computational burden. Thus, monocular depth estimation with superior performance and fast runtime can be achieved in testing phase by only using the lightweight Mono-Net. For the proposed framework, our core idea lies in: 1) how to design the Stereo-Net so that it can accurately estimate depth maps by fully exploiting the stereo information; 2) how to use the sophisticated Stereo-Net to improve the performance of Mono-Net. To this end, we propose a recursive estimation and refinement strategy for Stereo-Net to boost its performance of depth estimation. Meanwhile, a multi-space knowledge distillation scheme is designed to help Mono-Net amalgamate the knowledge and master the expertise from Stereo-Net in a multi-scale fashion. Experiments demonstrate that our method achieves the superior performance of monocular depth estimation in comparison with other state-of-the-art methods.

This article proposes a new Multi-Kink Quantile Regression (MKQR) model which assumes different linear quantile regression forms in different regions of the domain of the threshold covariate but are still continuous at kink points. First, we investigate parameter estimation, kink points detection and statistical inference in MKQR models. We propose an iterative segmented quantile regression algorithm for estimating both the regression coefficients and the locations of kink points. The proposed algorithm is much more computationally efficient than the grid search algorithm and not sensitive to the selection of initial values. Second, asymptotic properties, such as selection consistency of the number of kink points and asymptotic normality of the estimators of both regression coefficients and kink effects, are established to justify the proposed method theoretically. Third, a score test based on partial subgradients is developed to verify whether the kink effects exist or not. Test-inversion confidence intervals for kink location parameters are also constructed. Monte Carlo simulations and two real data applications on the secondary industrial structure of China and the triceps skinfold thickness of Gambian females illustrate the excellent finite sample performances of the proposed MKQR model. A new R package MultiKink is developed to easily implement the proposed methods.

Combining multiple patterning lithography (MPL) and optical proximity correction (OPC) pushes the limit of 193-nm wavelength lithography to go further. Considering that layout decomposition may generate plenty of solutions with diverse printabilities, relying on conventional mask optimization (MO) process to select the best candidate for manufacturing is computationally expensive. Therefore, an accurate and efficient printability estimation is crucial and can significantly accelerate the layout decomposition and MO (LDMO) flow. In this article, we propose a convolutional neural network (CNN)-based prediction and integrate it into our new high-performance LDMO framework. The optimization process can be considerably improved as the decomposition quality has been inferred in the early phase. To facilitate the network training and ensure better estimation accuracy, we develop sampling strategies for both layout and decomposition. Moreover, we enhance the layout sampling approach by adopting autoencoder to distance evaluation that promises superior sampling results. The experimental results demonstrate the effectiveness and the efficiency of the proposed algorithms.