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 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. Project page: https://li-yuetao.github.io/ActiveSplat/.

@article{li2025_2410.21955,
  title={ ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting },
  author={ Yuetao Li and Zijia Kuang and Ting Li and Qun Hao and Zike Yan and Guyue Zhou and Shaohui Zhang },
  journal={arXiv preprint arXiv:2410.21955},
  year={ 2025 }
}