Search papers, labs, and topics across Lattice.
This paper introduces GaussianSelector, a novel framework for lightweight human-guided object selection in 3D scenes that operates directly on Gaussian primitives without the need for retraining or dense viewpoint coverage. By coarsening dense Gaussians into superpoints and employing a continuity-weighted graph for selection, the method enables effective object selection from sparse views and minimal user input. Experimental results show that GaussianSelector achieves comparable selection quality to state-of-the-art methods while significantly reducing computational demands and interaction requirements, making it ideal for practical applications in scene editing and asset extraction.
Achieving high-quality 3D object selection with minimal user input and computational cost, GaussianSelector redefines the efficiency of scene editing.
Selecting a complete 3D object from a reconstructed scene with minimal user effort is essential for practical scene editing and embodied interaction. Existing 3DGS-based methods either retrain the Gaussian representation to embed per-object labels, or build dense multi-view SAM observations, both requiring heavy computation and dense viewpoint coverage that is rarely available in practice. We present GaussianSelector, a training-free framework for interactive 3D object selection from sparse views and sparse scribble guidance. Operating directly on native Gaussian primitives, we coarsen dense Gaussians into geometrically coherent superpoints and construct a continuity-weighted graph using appearance and spatial cues. Sparse user scribbles are lifted into 3D via visibility-aware transmittance coverage, and selection is solved as a global graph-cut energy minimization that propagates sparse evidence to a complete 3D object. This design naturally supports multi-round refinement, where users iteratively correct the selection from additional viewpoints to progressively improve the result. Experiments demonstrate that GaussianSelector achieves competitive selection quality against state-of-the-art multi-view SAM-based methods, while requiring significantly fewer interaction views and substantially lower computational overhead. These properties make it well suited for human-in-the-loop 3D scene editing and 3D asset extraction in real-world deployment scenarios.
