Search papers, labs, and topics across Lattice.
The paper introduces CoGeo-GS, a novel framework designed for controllable multi-object removal in 3D scenes, addressing challenges such as occlusions and semantic entanglement. By assigning concept-aware semantic tags to Gaussians, the method allows for flexible object selection and minimizes interference between objects, all within a single optimization stage. Experimental results show that CoGeo-GS significantly enhances visual quality and reconstruction fidelity compared to existing 3D Gaussian Splatting methods.
CoGeo-GS achieves superior multi-object removal in 3D scenes by integrating concept-driven tagging with geometry-aware completion, outperforming traditional methods in both quality and stability.
Multi-object removal in 3D scenes is challenging due to severe occlusions, semantic entanglement, and the difficulty of maintaining geometric and multi-view consistency. Existing 3D Gaussian Splatting (3DGS) methods perform well for single-object editing but scale poorly to multi-object scenarios, often requiring repetitive optimization and yielding unstable geometry in removed regions. We propose CoGeo-GS, a concept-driven framework for controllable multi-object removal in 3D scenes. CoGeo-GS assigns concept-aware semantic tags to Gaussians, enabling flexible object selection and reducing interference between foreground objects and background structures within a single optimization stage. To recover plausible geometry, we introduce a geometry-aware completion pipeline that combines monocular depth priors with diffusion-based refinement and boundary-aligned blending. A geometry-regularized refinement strategy further stabilizes reconstruction and preserves multi-view consistency. Experiments demonstrate that CoGeo-GS outperforms existing methods in visual quality and reconstruction fidelity.
