[
    {
        "id": "osp-23962",
        "type": "article-journal",
        "title": "CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments",
        "author": [
            {
                "family": "Chen",
                "given": "Feiyang"
            },
            {
                "family": "Hu",
                "given": "Jincheng"
            },
            {
                "family": "Chen",
                "given": "Yiduo"
            },
            {
                "family": "Li",
                "given": "Jihao"
            },
            {
                "family": "Liang",
                "given": "Yue"
            },
            {
                "family": "Gao",
                "given": "Bingzhao"
            },
            {
                "family": "Huang",
                "given": "Yanjun"
            },
            {
                "family": "Zhang",
                "given": "Yuanjian"
            }
        ],
        "URL": "https://omanscience.com/en/articles/crowdocc-monocular-semantic-scene-completion-for-quadruped-robots-in-crowded-indoor-environments",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Monocular semantic scene completion (SSC) for quadruped robots remains underexplored in real crowded indoor environments, where human-scene occlusion disrupts static geometry and human occupancy predictions are often incomplete or spatially misplaced. We present CrowdOcc, an RGB-D dataset and monocular SSC framework for this setting. CrowdOcc contains 25.1K frames from 11 indoor scenes, with semantic occupancy annotations constructed through static dynamic decoupling. Our framework combines: (i) Normal Guided Scene Geometry Fusion (NGSGF) to complement depth-aware lifting with surface-normal cues for occlusion robust geometry; and (ii) Human-Centric Sparse Interaction (HCSI) to selectively model human-human and local human scene relations in 3D. Our method achieves state-of-the-art SSC performance on CrowdOcc's scene-disjoint test set, reaching 15.80 IoU, 11.40 mIoU, and 46.23 Human IoU, demonstrating generalization to unseen indoor scenes."
    }
]