Image restoration is a prominent field of research in computer vision. Restoring broken paintings, especially ancient Chinese artworks, is a significant challenge for current restoration models. The difficulty lies in realistically reinstating the intricate and delicate textures inherent in the original pieces. This process requires preserving the unique style and artistic characteristics of the ancient Chinese paintings. To enhance the effectiveness of restoring and preserving traditional Chinese paintings, this paper presents a framework called Sketch-Guided Restoration Generative Adversarial Network, termd SGRGAN. The framework employs sketch images as structural priors, providing essential information for the restoration process. Additionally, a novel Focal block is proposed to enhance the fusion and interaction of textural and structural elements. It is noteworthy that a BiSCCFormer block, incorporating a Bi-level routing attention mechanism, is devised to comprehensively grasp the structural and semantic details of the image, including its contours and layout. Extensive experiments and ablation studies on MaskCLP and Mural datasets demonstrate the superiority of the proposed method over previous state-of-the-art methods. Specifically, the model demonstrates outstanding visual fidelity, particularly in the restoration of landscape paintings. This further underscores its efficacy and universality in the realm of cultural heritage preservation and restoration.

Existing image super-resolution methods have made remarkable advancements in enhancing the visual quality of real-world images. However, when it comes to restoring Chinese paintings, these methods encounter unique challenges. This is primarily due to the difficulty in preserving intricate non-realistic details and capturing comple semantic information with high dimensionality. Moreover, the preservation of the original artwork’s distinct style and subtle artistic nuances further amplifies this complexity. To address these challenges and effectively restore traditional Chinese paintings, we propose a Convolutional Super-Resolution Generative Adversarial Network for Chinese landscape painting super-resolution, termed ConvSRGAN. We employ Enhanced Adaptive Residual Module to delve deeply into multi-scale feature extraction in images, incorporating an Enhanced High-Frequency Retention Module that leverages an Adaptive Deep Convolution Block to capture fine-grained high-frequency details across multiple levels. By combining the Multi-Scale Structural Similarity loss with conventional losses, our ConvSRGAN ensures that the model produces outputs with improved fidelity to the original image’s texture and structure. Experimental validation demonstrates significant qualitative and quantitative results when processing traditional paintings and murals datasets, particularly excelling in high-definition reconstruction tasks for landscape paintings. The reconstruction effect showcases enhanced visual fidelity and liveliness, thus affirming the effectiveness and applicability of our approach in cultural heritage preservation and restoration.

How to migrate text-to-image models based on pre-trained diffusion models to adapt them to domain generation tasks is a common problem. In particular, the generation task for Chinese landscape paintings with unique characteristics suffers from a scarcity of fine-grained contextual details specific to such artwork. Moreover, the use of substantial amounts of non-landscape painting data during pre-training predisposes the model to be swayed by alternative visual styles, thereby leading to generated images that inadvertently lack the distinctive traits inherent to Chinese paintings. In this paper, we propose a Fine-grained Hierarchical Semantic Adapter for Chinese landscape paintings generation, namely FHS-adapter. The method orchestrates the diffusion process in a batch-wise manner, leveraging external fine-grained multi-perspective information to guide it. It gradually diminishes the influence of other style images embedded in the pre-trained diffusion model, ultimately preserving a greater number of landscape painting elements. The encoder was also replaced with the Taiyi-CLIP encoder, which is adapted for Chinese. We propose T2ICLP, a multimodal dataset containing 10,000 high-quality image-text pairs of Chinese landscape paintings. Unlike previous datasets, this dataset extracts fine-grained textual information from four perspectives, including Meta, Description, Sentiment, Poem. We compared the proposed model with the mainstream diffusion-based T2I models. Through an anonymous user study, our FHS-adapter method performs well in simulating various aspects such as brushwork, e.g.‘Gou, Cun, Dian, Ran’ means hooking, texturing, dotting, and dyeing, compositional space, elemental proportions, and color usage of different painting genres and artists. Our dataset is available at https://github.com/T2ICLP/t2iclp.

Over 1.3 million people die annually in traffic accidents, and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems. In modern industrial and technological applications and collaborative edge intelligence, control systems are crucial for ensuring efficiency and safety. However, deficiencies in these systems can lead to significant operational risks. This paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control, particularly the limitations of traditional Proportional-Integral-Derivative (PID) controllers in managing nonlinear and time-varying dynamics, such as varying road conditions and vehicle behavior, which often result in substantial discrepancies between desired and actual speeds, as well as inefficiencies due to manual parameter adjustments. The paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation (BP) neural networks to enhance robustness and adaptability. The BP neural network is first trained to capture the nonlinear dynamic characteristics of the vehicle. The trained network is then combined with the PID controller to form a hybrid control strategy. The output layer of the neural network directly adjusts the PID parameters (, , ), optimizing performance for specific driving scenarios through self-learning and weight adjustments. Simulation experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods, with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 s. Furthermore, real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions, ensuring consistent speed maintenance and enhancing overall system performance.