[
    {
        "id": "osp-24227",
        "type": "article-journal",
        "title": "Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation",
        "author": [
            {
                "family": "Shen",
                "given": "Zhijie"
            },
            {
                "family": "Lin",
                "given": "Chunyu"
            },
            {
                "family": "Zheng",
                "given": "Shuai"
            },
            {
                "family": "Li",
                "given": "Feng"
            },
            {
                "family": "Cong",
                "given": "Runmin"
            },
            {
                "family": "Bai",
                "given": "Huihui"
            },
            {
                "family": "Zhao",
                "given": "Yao"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches."
    }
]