[
    {
        "id": "osp-19924",
        "type": "article-journal",
        "title": "RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation",
        "author": [
            {
                "family": "Kim",
                "given": "Minsu"
            },
            {
                "family": "Choe",
                "given": "Jaesung"
            },
            {
                "family": "Lee",
                "given": "Jiwoo"
            },
            {
                "family": "Wang",
                "given": "Yu-Chiang Frank"
            },
            {
                "family": "Kim",
                "given": "Seon Joo"
            }
        ],
        "URL": "https://omanscience.com/en/articles/relationvggt-visual-geometry-transformers-for-3d-spatial-relation-segmentation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has followed suit -- yet existing methods remain confined to object-centric perception, neglecting spatial relations between objects. We formulate 3D spatial relation segmentation in a feed-forward, pose-free multi-view setting: given a visually specified subject and a relational text query, the model segments the target across views without receiving its category name. To this end, we propose RelationVGGT, a novel feed-forward framework that integrates semantic features from a visual foundation model with geometry-aware representations from a 3D geometry foundation model and leverages a relation transformer for subject-conditioned, cross-view relation prediction -- requiring neither per-scene optimization nor known camera poses. We additionally provide a fully automated annotation pipeline built on ScanNet++ with VLMs and LLMs, enabling scalable training data generation for this new task."
    }
]