Zijia Kuang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zijia Kuang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Guyue Zhou
Tsinghua University
1 shared publication - Qun Hao
Changchun University of Science and Technology
1 shared publication - Shaohui Zhang
Beijing Institute of Technology
1 shared publication - Ting Li
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China
1 shared publication - Yuetao Li
School of Optics and Photonics, Beijing Institute of Technology, Beijing, China
1 shared publication - Zike Yan
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- Top Cited Papers
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (8) , 8099-8106
ActiveSplat: High-Fidelity Scene Reconstruction Through Active Gaussian Splatting
We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establishes a unified framework for online mapping, viewpoint selection, and path planning. The key to ActiveSplat is a hybrid map representation that integrates both dense information about the environment and a sparse abstraction of the workspace. Therefore, the system leverages sparse topology for efficient viewpoint sampling and path planning, while exploiting view-dependent dense prediction for viewpoint selection, facilitating efficient decision-making with promising accuracy and completeness. A hierarchical planning strategy based on the topological map is adopted to mitigate repetitive trajectories and improve local granularity given limited time budgets, ensuring high-fidelity reconstruction with photorealistic view synthesis. Extensive experiments and ablation studies validate the efficacy of the proposed method in terms of reconstruction accuracy, data coverage, and exploration efficiency. The released code will be available on our project page
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (8) , 8099-8106
Top Cited PapersActiveSplat: High-Fidelity Scene Reconstruction Through Active Gaussian Splatting
We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establishes a unified framework for online mapping, viewpoint selection, and path planning. The key to ActiveSplat is a hybrid map representation that integrates both dense information about the environment and a sparse abstraction of the workspace. Therefore, the system leverages sparse topology for efficient viewpoint sampling and path planning, while exploiting view-dependent dense prediction for viewpoint selection, facilitating efficient decision-making with promising accuracy and completeness. A hierarchical planning strategy based on the topological map is adopted to mitigate repetitive trajectories and improve local granularity given limited time budgets, ensuring high-fidelity reconstruction with photorealistic view synthesis. Extensive experiments and ablation studies validate the efficacy of the proposed method in terms of reconstruction accuracy, data coverage, and exploration efficiency. The released code will be available on our project page