|
Xi Liu Welcome to my homepage! I am a second‑year Computer Science PhD student at Clemson University, advised by Prof. Siyu Huang. I earned my M.Sc. in Computer Science from DIKU, University of Copenhagen—where I was advised by Prof. Serge Belongie—and remain an affiliated researcher at the Pioneer Center for AI. Prior to DIKU, I completed my B.S. in Computer Science and Technology at Jilin University. My research interests span generative models, differentiable SVGs, 3D reconstruction, and 3D world understanding. I am actively seeking internship opportunities and am available at any time and would love to collaborate with organizations working at the intersection of LLM, generative model and 3D vision. Feel free to contact me if my work aligns with your team’s goals! |
|
|
Bézier Splatting for Fast and Differentiable Vector Graphics
Xi Liu, Chaoyi Zhou, Nanxuan Zhao, Siyu Huang, arxiv, 2025 project page / arXiv This work introduces a new differentiable VG representation, dubbed Bézier splatting, that enables fast yet high-fidelity VG rasterization. |
|
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Xi Liu*, Chaoyi Zhou*, Siyu Huang, NeurIPS, 2024 project page / arXiv We leverage 2D video diffusion priors to address the challenging 3D view consistency problem, reformulating it as achieving temporal consistency within a video generation process. |
|
Latent Radiance Fields with 3D-aware 2D Representations
Chaoyi Zhou*, Xi Liu*, Feng Luo, Siyu Huang ICLR, 2025 project page / arXiv / code In this work, we propose a method to achieve 3D-aware 2D representations and enable 3D reconstruction in the latent space. |
Academic ServiceConference Reviewer: ICML 2025, ICLR 2025, NeurIPS 2024. |