Conventional metasurface design methods usually require a lot of computational resources and time, meaning they fail to satisfy the efficient, rapid design on demand. On account of this, we branch out of the conventional metasurface design methods by attempting to relate the emerging discipline of artificial intelligence to a traditional physical area. With our method, named AMID, metasurface structures are designed inversely where they can be computed directly by simply proposing and inputting the desired design targets into AMID. AMID greatly simplifies conventional methods that call for not only sufficient professional knowledge but also trial and error through simulation softwares. According to the design results, unit cells of metasurfaces are successfully computed, which verifies the availability of AMID and improves the design efficiency in the meanwhile.

Recent multimodal fake news detection methods often use the consistency between textual and visual contents to determine the truth or fake of news information. Higher levels of textual-visual consistency typically lead to a greater likelihood of classifying a news item as real. However, a critical observation reveals that creators of most fake news intentionally select images that align with the textual content, thereby enhancing the credibility of the news. Consequently, high consistency between textual and visual contents alone cannot guarantee the authenticity of the information. To address this problem, we introduce a novel approach termed Multimodal Consistency-based Suppression Factor to modulate the significance of textual-visual consistency in information assessment. When the textual-visual matching is high, this suppression factor reduces the influence of consistency during the judgment process. Moreover, we use contrastive language-image pre-training (CLIP) model to extract features and measure the consistency level between modalities to guide multimodal fusion. In addition, we also use a method of compressing and fusing modal information based on variational autoencoder (VAE) to reconstruct CLIP features, learning the shared representation of different modal information of CLIP. Finally, extensive experiments were conducted on three publicly datasets, Weibo, Twitter, and Weibo21, and the results confirmed that our method outperformed the state-of-the-art methods in the field and had 0.8%, 2.6%, and 4.1% effect improvement on the accuracy rate.

Traditional Chinese patterns, as one of the core cultural heritage carriers, face inheritance challenges due to traditional design’s heavy reliance on professional expertise and lengthy cycles. The rise of Artificial Intelligence Generated Content (AIGC) has introduced a human-intelligence collaborative paradigm to address these issues—this article focuses on leveraging AIGC for intelligent design of traditional Chinese patterns. Specifically, a dataset of traditional Chinese patterns was first constructed, featuring 30,000 images represented by Tuanke patterns. Subsequently, ChiPa, an intelligent design method tailored to traditional Chinese patterns, was proposed. This method enables simultaneous control over both the content and color. ChiPa’s core is a novel Structure Projector (Feature Map Mixture + Latent Space Mapper with MCConv), which maps sketches to StyleGAN’s latent space to generate structurally accurate grayscale Tuanke patterns. For color customization, ChiPa employs an arbitrary style transfer module to render grayscale patterns via user-specified references. Extensive experiments validate ChiPa’s superiority: it outperforms SOTA methods in all metrics; 3 domain experts and 30 volunteers rated it highest in structural standardization, stylistic consistency, and symbolic accuracy. Case studies demonstrate applications in cultural (e.g., packaging) and commercial (e.g., sofa upholstery) products. ChiPa lowers public participation barriers, expands Tuanke patterns’ carriers, and promotes living conservation and dissemination of Chinese traditional cultural heritage.

The study of ancient textile patterns not only enriches historical material but also inspires modern costume art design. Recent developments in computer vision technology provide novel analytical methods for the study of ancient textile patterns. As contours are one of the most significant features in computer vision tasks, contour extraction serves as a prerequisite to accomplishing intelligent understanding and automatic design of textile patterns. In this paper, a perception-consistent contour extraction method (ViCo) that simulates the human visual system from the retina, the lateral geniculate nucleus (LGN), to the V1 area in the cortex is proposed, along with an ancient textile pattern dataset represented by TuanKe in the Chinese Tang dynasty. Experiments were conducted both qualitatively and quantitatively to verify the effectiveness of the proposed method on the TuanKe dataset. Analysis of the results implies the effectiveness of ViCo because the retinal and LGN filter enhances edge information and restrains tiny pixel changes, and the cortex simulation is direction selective. This study is among the initial efforts to employ computer vision technology for ancient textile pattern studies. The study presents a TuanKe dataset and a novel bio-inspired contour extraction method, which has significant historical research importance, fabric art design inspiration, and computer application value.

In computer vision, zero-shot image restoration—a technique enabling degraded image restoration without large-scale paired training data—has emerged as a pivotal technique for scenarios where data is limited or paired training data is challenging to obtain. However, existing methods face two key limitations: data consistency preservation remains challenging for out-of-domain data, and degradation process alignment is difficult when the degradation mechanism is not mathematically predetermined. To address these issues, this paper presents a novel zero-shot image restoration method (FIR-SDE). Traditional generation-oriented diffusion models (designed for image creation) are replaced with restoration-oriented models (specialized for degradation repair), expanding the range of effectively restorable images. To mitigate the noise offset (discrepancies between real and model-simulated degradation) and to enhance the alignment, a multi-step optimization strategy is employed, which evaluates the distance between real and simulated degraded images via frequency domain distribution. Experiments were conducted on two image restoration tasks (image deraining and inpainting) using three public datasets (AFHQ-dog, CelebA, and FFHQ), with Gaussian blur and motion blur superimposed as noise offsets. Results demonstrate that FIR-SDE method outperforms competitive methods in restoration quality and noise resistance. By eliminating data space constraints and exhibiting robustness against noise offsets, FIR-SDE offers a more flexible and efficient solution to broaden the practical applicability of zero-shot image restoration.