Biography

I am pursuing my M.S. degree in Polytechnic Institute, Zhejiang University, Hangzhou, China. My major research interest is Simultaneous Localization and Mapping(SLAM).

Research and Interests

• Simultaneous Localization and Mapping
• Visual Localization

Publications

• Yijia Xie, Yuhang Lin, Laijian Li, Lina Liu, Xiaobin Wei, Yong Liu, and Jiajun Lv. Hash-GS: Anchor-Based 3D Gaussian Splatting with Multi-Resolution Hash Encoding for Efficient Scene Reconstruction. In 2025 IEEE International Conference on Robotics and Automation (ICRA), pages 13964-13971, 2025.
  [BibTeX] [Abstract] [DOI] [PDF]

  Realistic 3D object and scene reconstruction is pivotal in advancing fields such as world model simulation and embodied intelligence. In this paper, we introduce Hash-GS, a storage-efficient method for large-scale scene reconstruction using anchor-based 3D Gaussian Splatting (3DGS). The vanilla 3DGS struggles with high memory demands due to the large number of primitives, especially in complex or extensive scenes. Hash-GS addresses these challenges with a compact representation by leveraging high-dimensional features to parameterize primitive properties, stored in compact hash tables, which reduces memory usage while preserving rendering quality. It also incorporates adaptive anchor management to efficiently control the number of anchors and neural Gaussians. Additionally, we introduce an analytic 3D smoothing filter to mitigate aliasing and support Level-of-Detail for optimized rendering across varying intrinsic parameters. Experimental results on several datasets demonstrate that Hash-GS improves storage efficiency while maintaining competitive rendering performance, especially in large-scale scenes.

  @inproceedings{xie2025hash,
  title = {Hash-GS: Anchor-Based 3D Gaussian Splatting with Multi-Resolution Hash Encoding for Efficient Scene Reconstruction},
  author = {Yijia Xie and Yuhang Lin and Laijian Li and Lina Liu and Xiaobin Wei and Yong Liu and Jiajun Lv},
  year = 2025,
  booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
  pages = {13964-13971},
  doi = {10.1109/ICRA55743.2025.11128324},
  abstract = {Realistic 3D object and scene reconstruction is pivotal in advancing fields such as world model simulation and embodied intelligence. In this paper, we introduce Hash-GS, a storage-efficient method for large-scale scene reconstruction using anchor-based 3D Gaussian Splatting (3DGS). The vanilla 3DGS struggles with high memory demands due to the large number of primitives, especially in complex or extensive scenes. Hash-GS addresses these challenges with a compact representation by leveraging high-dimensional features to parameterize primitive properties, stored in compact hash tables, which reduces memory usage while preserving rendering quality. It also incorporates adaptive anchor management to efficiently control the number of anchors and neural Gaussians. Additionally, we introduce an analytic 3D smoothing filter to mitigate aliasing and support Level-of-Detail for optimized rendering across varying intrinsic parameters. Experimental results on several datasets demonstrate that Hash-GS improves storage efficiency while maintaining competitive rendering performance, especially in large-scale scenes.}
  }