Xufeng Li — accepted AI-conference papers

2026

Zero-Shot VISUAL GROUNDING in 3D Gaussians via View Retrieval

Liwei Liao, Xufeng Li, Xiaoyun Zheng, Feng Gao, Ronggang Wang

ICASSP 2026poster

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the implicit representation of spatial textures in 3D Gaussian Spla…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling

Xiaoyun Zheng, Liwei Liao, Xufeng Li, Jianbo Jiao, Rongjie Wang, Feng Gao +2

CVPR 2024poster

High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested in developing various capture systems and reconstruction algorithms recent advancements still struggle with loose or ov…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗