CSChenxi Song

Chenxi Song

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Chenxi Song has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation

    by Chi Zhang, Yiwen Chen, Yijun Fu, Wei Cheng, Zhenglin Zhou, Wenjia Jiang, Zhibin Wang, Bin Fu, Tao Chen, Gang Yu, et al.

    The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models. Nevertheless, the limited availability of diverse 3D resources presents significant challenges to learning. In this paper, we present a novel method for generating high-quality, stylized 3D avatars that utilizes pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training. Our method leverages the comprehensive priors of appearance and geometry offered by image-text diffusion models to generate multi-view images of avatars in various styles. During data generation, we employ poses extracted from existing 3D models to guide the generation of multi-view images. To handle inaccurate pose annotations of stylized images, we investigate view-specific prompts and develop a coarse-to-fine discriminator for GAN training. Additionally, we develop a latent diffusion model within the style space of StyleGAN to enable the generation of avatars based on image or text inputs. Our approach demonstrates superior performance over current state-of-the-art methods in terms of visual quality and diversity of the produced avatars.


  • FewarNet: An Efficient Few-Shot View Synthesis Network Based on Trend Regularization

    by Chenxi Song, Shigang Wang, Jian Wei, Yan Zhao

    Novel view synthesis from existing inputs remains a research focus in computer vision. Predicting views becomes more challenging when only a limited number of views are available. This challenge is commonly referred to as the few-shot view synthesis problem. Recently, various strategies have emerged for few-shot view synthesis, such as transfer learning, depth supervision, and regularization constraints. However, transfer learning relies on massive scene data, depth supervision is affected by input depth quality, and regularization causes increased computational costs or impaired generalization. To address these issues, we propose a new few-shot view synthesis framework called FewarNet that introduces trend regularization to leverage depth structural features and a warping loss to supervise depth estimation, possessing the advantages of existing few-shot strategies, enabling high-quality novel view prediction with generalization and efficiency. Specifically, FewarNet consists of three stages: fusion, warping, and rectification. In the fusion stage, a fusion network is introduced to estimate depths using scene priors from coarse depths. In the warping stage, the predicted depths are used to guide the warping of the input views, and a distance-weighted warping loss is proposed to correctly guide depth estimation. To further improve prediction accuracy, we propose trend regularization which imposes penalties on depth variation trends to provide depth structural constraints. In the rectification stage, a rectification network is introduced to refine occluded regions in each warped view to generate novel views. Additionally, a rapid view synthesis strategy that leverages depth interpolation is designed to improve efficiency. We validate the method’s effectiveness and generalization on various datasets. Given the same sparse inputs, our method demonstrates superior performance in quality and efficiency over state-of-the-art few-shot view synthesis methods.


  • Multistability of S-Asymptotically ω-Periodic Solutions for Fractional-Order Neural Networks with Time Variable Delays

    by Chenxi Song, Sitian Qin, Jiqiang Feng

    This paper explores the multistability of S-asymptotically $\omega$-periodic solutions for fractional-order neural networks with time variable delays (FVDNNs). Benefited from the geometrical configuration of the nonlinear and non-monotonic activation function, we prove the coexistence of $(K+1)^{n}$ S-asymptotically $\omega$-periodic solutions with multiple asymptotical stability, where K is a positive integer. In contrast to the previous works, the obtained results extensively raise the amount of S-asymptotically $\omega$-periodic solutions of FVDNNs in this paper. Besides, two numerical examples are shown to illustrate the feasibility of obtained results.

  • Hole filling algorithm for image array of one-dimensional integrated imaging

    by Yixue Han, Shigang Wang, Jian Wei, Chenxi Song

    Compared to traditional integrated imaging, the one-dimensional integrated imaging system abandons the stereoscopic effect in the vertical direction, leaving only the stereoscopic effect in the horizontal direction. While satisfying the stereoscopic perception, it greatly reduces the storage space of data and alleviates the large attenuation of resolution caused by integrated imaging. However, at present, there is no 3D film source suitable for a one-dimensional integrated imaging system. In order to address this problem, we propose an array image generation and padding algorithm based on a one-dimensional integrated imaging system. First, based on the theory of geometric optics and DIBR(Depth-image Based Rendering), we use depth maps to simulate viewpoint images at arbitrary locations. In the process, we classify the points mapped to the viewpoint image to make the generated viewpoint image more accurate. Secondly, when conducting hole filling, we first use the optical flow method to fill the large holes inside the image. We extract the edge of the hole, compare the depth values on both sides of the edge, and estimate the depth value of the hole by taking the optical flow value on the larger side, so as to calculate the mapping block of the hole on the reference frame. Finally, the other holes are filled using the Criminisi image restoration algorithm.