Haijie LI — accepted AI-conference papers

2025

InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception

Haijie Li, Yanmin Wu, Jiarui Meng, Qiankun Gao, Zhiyao Zhang, Ronggang Wang +1

CVPR 2025poster

3D scene understanding is vital for applications in autonomous driving, robotics, and augmented reality. However, scene understanding based on 3D Gaussian Splatting faces three key challenges: (i) an imbalance between appearance and semantics, (ii) inconsistencies in object boundaries, and (iii) dif…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

Yanmin Wu, Jiarui Meng, Haijie LI, Chenming Wu, Yahao Shi, Xinhua Cheng +5

NeurIPS 2024poster

This paper introduces OpenGaussian, a method based on 3D Gaussian Splatting (3DGS) that possesses the capability for 3D point-level open vocabulary understanding. Our primary motivation stems from observing that existing 3DGS-based open vocabulary methods mainly focus on 2D pixel-level parsing. Thes…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗