Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gaussian surfels as a unified representation to progressively reconstruct unknown objects with both photorealistic appearance and accurate geometry. Addressing the limitations of conventional opacity or depth-based cues, we introduce a geometry-aware viewpoint evaluation pipeline that explicitly models back-face visibility and occlusion-aware multi-view covisibility, reliably identifying under-reconstructed regions even on geometrically complex objects. Furthermore, to overcome the limitations of greedy planning strategies, ObjSplat employs a next-best-path (NBP) planner that performs multi-step lookahead on a dynamically constructed spatial graph. By jointly optimizing information gain and movement cost, this planner generates globally efficient trajectories. Extensive experiments in simulation and on real-world cultural artifacts demonstrate that ObjSplat produces physically consistent models within minutes, achieving superior reconstruction fidelity and surface completeness while significantly reducing scan time and path length compared to state-of-the-art approaches. Project page: https://li-yuetao.github.io/ObjSplat-page/ .

翻译：自主高保真物体重建是创建数字资产与弥合机器人学中仿真-现实差距的基础。我们提出了ObjSplat，一种主动重建框架，它利用高斯面元作为统一表示，逐步重建具有照片级真实感外观与精确几何形状的未知物体。针对传统基于不透明度或深度线索的局限性，我们引入了一种几何感知的视点评估流程，该流程显式建模背面可见性与遮挡感知的多视角共可见性，即使在几何结构复杂的物体上也能可靠地识别重建不足的区域。此外，为克服贪婪规划策略的局限，ObjSplat采用了一种基于动态构建空间图进行多步前瞻的"最优下一条路径"规划器。通过联合优化信息增益与移动成本，该规划器能生成全局高效的轨迹。在仿真环境及真实世界文化遗产上的大量实验表明，ObjSplat可在数分钟内生成物理一致的模型，在显著减少扫描时间与路径长度的同时，实现了优于现有先进方法的重建保真度与表面完整性。项目页面：https://li-yuetao.github.io/ObjSplat-page/。