I am currently advancing through my second year of a PhD program at Shenzhen University, under the supervision of Prof. Hui Huang, with a focus on Computer Graphics. My journey in this field is driven by a passion for innovation and a commitment to excellence.
If you share an interest in computer graphics, I would be delighted to hear from you. Feel free to reach out to me at qixuemaa@gmail.com for any academic discussions.
I eagerly anticipate engaging in discussions with fellow enthusiasts and professionals in the field!
I am interested in Computer Graphics, Computer Vision, and Generative Models, particularly in the processing of 3D point clouds and the structural reconstruction and generation of 3D models.
3D generative models aim to create detailed and realistic meshes, but current methods face memory and surface realism issues. The GenUDC framework solves these problems using Unsigned Dual Contouring (UDC) for mesh representation.
We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-based representation for improved coherence in learning 3D wireframe structures.
This study introduces a method for extracting 3D road network structures from large-scale point cloud scenes, addressing challenges by utilizing L1 medial axis extraction and applying flexible constraints.