ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction

TL;DR

ObjSplat introduces a geometry-aware active reconstruction framework using Gaussian surfels, enabling efficient, high-fidelity object modeling with improved view planning and occlusion handling, demonstrated on complex objects in simulation and real-world settings.

Contribution

It proposes a novel geometry-aware viewpoint evaluation and a multi-step lookahead planner for active object reconstruction, improving efficiency and accuracy over prior methods.

Findings

Achieves high-fidelity, complete reconstructions within minutes.

Reduces scan time and path length significantly.

Outperforms state-of-the-art approaches in fidelity and efficiency.

Abstract

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/ .