主动选择视角，用高斯点云实现高精度实时建模
ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting
- 用稀疏拓扑+稠密预测融合地图，兼顾效率与精度
- 在有限时间内实现90%以上覆盖率和毫米级重建精度
- 适合机器人自主探索、AR/VR场景重建等应用
我们提出ActiveSplat，一个基于高斯点云的自主高保真场景重建系统。该系统利用高效且逼真的渲染能力，构建了在线地图构建、视角选择与路径规划的统一框架。其核心是混合地图表示：既包含环境的稠密信息，又保留工作空间的稀疏抽象。由此，系统以稀疏拓扑进行高效的视角采样与路径规划，同时利用视图相关的稠密预测完成视角选择，实现高效决策并保持优异的准确性和完整性。采用基于拓扑图的分层规划策略，有效减少重复轨迹，在有限时间预算下提升局部细节粒度，确保高保真重建与逼真视觉合成。大量实验与消融研究验证了该方法在重建精度、数据覆盖范围与探索效率上的有效性。代码将发布于项目主页：https://li-yuetao.github.io/ActiveSplat/
原文摘要 · Abstract (English)
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: https://li-yuetao.github.io/ActiveSplat/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。