{"ID":5675131,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T04:57:17.014105577Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01708","arxiv_id":"2607.01708","title":"Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement","abstract":"Reliable instance-level scene understanding is a fundamental prerequisite for object-level interactions and high-fidelity 3D representations. While current methods often leverage 2D foundation segmentation models to obtain these priors, their 2D-centric design typically yields fragmented masks and inconsistent predictions across different views. To address these issues, we propose a novel framework that produces consistent 2D instance masks to guide the optimization of 3D Gaussian Splatting (3DGS) feature fields. Our framework consists of three main stages. (1) Multi-Cue Extraction that generates synergistic semantic, geometric, and structural priors from input images. (2) Multi-Cue-Guided Mask Merging process that consolidates fragmented masks using a composite merge score derived from semantic, depth, and edge cues. (3) Cross-View Mask Matching that establishes globally consistent identity assignments across all viewpoints. By transforming viewpoint-specific segments into coherent 3D primitives, our approach enables stable 3D instance segmentation and effective downstream editing tasks. Experiments demonstrate that our method significantly improves cross-view consistency and segmentation stability over existing baselines while maintaining high-fidelity photometric reconstruction.","short_abstract":"Reliable instance-level scene understanding is a fundamental prerequisite for object-level interactions and high-fidelity 3D representations. While current methods often leverage 2D foundation segmentation models to obtain these priors, their 2D-centric design typically yields fragmented masks and inconsistent predicti...","url_abs":"https://arxiv.org/abs/2607.01708","url_pdf":"https://arxiv.org/pdf/2607.01708v1","authors":"[\"Hyunjoon Park\",\"Donghyeon Cho\"]","published":"2026-07-02T05:00:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}