O3N: 都市自律エージェントのための全方位オープンボキャブラリ占有予測
O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Urban Autonomous Agents
単一の全方位RGB画像から360度の3D占有を予測する初のオープンボキャブラリ手法を提案し、極座標スパイラルMambaと視覚・ボクセル・テキストの整合機構で高精度かつ汎化性能を実現した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Mengfei Duan, Hao Shi, Fei Teng, Guoqiang Zhao, Yuheng Zhang, Zhiyong Li, Kailun Yang
分類: cs.CV, cs.RO, eess.IV
原文アブストラクト
Understanding and reconstructing the 3D world through omnidirectional perception is becoming increasingly important for intelligent transportation and urban autonomous agents operating in shared spaces. However, existing vision-based 3D occupancy prediction methods are constrained by limited perspective inputs and a predefined training distribution, making them difficult to apply to embodied agents that require comprehensive and safe perception of scenes in open-world exploration. To address this, we present O3N, the first framework for open-vocabulary occupancy prediction from a single omnidirectional RGB image. O3N embeds omnidirectional voxels in a polar-spiral topology via the Polar-spiral Mamba (PsM) module, enabling continuous spatial representation and long-range context modeling across 360{\deg}. The Occupancy Cost Aggregation (OCA) module introduces a principled mechanism for unifying geometric and semantic supervision within the voxel space, ensuring consistency between the reconstructed geometry and the underlying semantic structure. Moreover, Natural Modality Alignment (NMA) establishes a gradient-free alignment pathway that harmonizes visual features, voxel embeddings, and text semantics, forming a consistent ``pixel-voxel-text'' representation triad. Extensive experiments on multiple models demonstrate that our method not only achieves state-of-the-art performance on QuadOcc and Human360Occ benchmarks but also exhibits remarkable cross-scene generalization and semantic scalability, highlighting the potential of O3N for scalable open-world 3D scene understanding. The source code will be made publicly available at https://github.com/MengfeiD/O3N
