Given the limited availability of multi-view information, research on 3D data and 3D reconstruction of Chinese paintings is scarce. Therefore, this paper proposes an innovative method called 3DTGC for the 3D reconstruction of Chinese painting elements generated from text. First, a text-to-image module generates images of Chinese painting elements from text. Then, a multi-view generation module handles multi-view synthesis. Through a series of preprocessing steps, this module creates six fixed-view images from a single image, which are used to generate a local light field fusion dataset. Next, the generated local light field fusion dataset is input into a neural radiation field synthesis module for further optimization of 3D information representation. Finally, a detailed mesh structure is created in the mesh generation module based on the results of the first two steps. Compared with several state-of-the-art 3D reconstruction methods, this framework demonstrates significant advantages in both visualization and technical performance. Furthermore, 3DTGC effectively addresses the multifaceted problem commonly encountered by other algorithms when processing traditional Chinese painting data, thereby improving reconstruction quality and robustness.

The style tranfer of Chinese landscape paintings offering new avenues for the digital preservation and inheritance of cultural heritage. In recent years, deep learning technologies have enabled style transfer between different images, achieving lifelike effects. Style transfer in Chinese landscape paintings aims to preserve the unique paintings skills of ancient Chinese painters, but faces three main challenges: ① The lack of high-quality datasets of traditional Chinese landscape paintings. ② The oversight of the unique techniques and ink details specific to traditional Chinese landscape paintings. ③ The gap between the style transfer outcomes and real landscape paintings. To address these deficiencies, this paper first introduces a Chinese landscape paintings dataset for style transfer, STCLP, which contains 4281 high-quality images of Chinese landscape paintings and natural landscapes. A generative adversarial network of style transfer in Chinese landscape painting based on spectral normalization is proposed, termed SN-CLPGAN. Additionally, it introduces the use of residual-in-residual dense blocks (RRDB) with reflect padding layers in the generator to learn the distinctive brushstrokes and techniques of Chinese landscape paintings. Furthermore, it employs the multi-scale structural similarity index measure (MS-SSIM) loss to minimize pixel-level differences between images, thereby producing images closer to traditional paintings in terms of color and pigmentation. Finally, the U-Net discriminator fused with SN is utilized to enhance the textural details of images, ensuring the stability of the model training process. Extensive experiments validate the effectiveness and advancement of the proposed method in the task of style transfer for Chinese landscape paintings.