O3N: Omnidirectional Open-Vocabulary Occupancy Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duan, Mengfei, Shi, Hao, Teng, Fei, Zhao, Guoqiang, Zhang, Yuheng, Li, Zhiyong, Yang, Kailun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917335696146432
author Duan, Mengfei
Shi, Hao
Teng, Fei
Zhao, Guoqiang
Zhang, Yuheng
Li, Zhiyong
Yang, Kailun
author_facet Duan, Mengfei
Shi, Hao
Teng, Fei
Zhao, Guoqiang
Zhang, Yuheng
Li, Zhiyong
Yang, Kailun
contents Understanding and reconstructing the 3D world through omnidirectional perception is an inevitable trend in the development of autonomous agents and embodied intelligence. However, existing 3D occupancy prediction methods are constrained by limited perspective inputs and 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 purely visual, end-to-end Omnidirectional Open-vocabulary Occupancy predictioN framework. 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°. 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, paving the way toward universal 3D world modeling. The source code will be made publicly available at https://github.com/MengfeiD/O3N.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12144
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle O3N: Omnidirectional Open-Vocabulary Occupancy Prediction
Duan, Mengfei
Shi, Hao
Teng, Fei
Zhao, Guoqiang
Zhang, Yuheng
Li, Zhiyong
Yang, Kailun
Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
Understanding and reconstructing the 3D world through omnidirectional perception is an inevitable trend in the development of autonomous agents and embodied intelligence. However, existing 3D occupancy prediction methods are constrained by limited perspective inputs and 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 purely visual, end-to-end Omnidirectional Open-vocabulary Occupancy predictioN framework. 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°. 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, paving the way toward universal 3D world modeling. The source code will be made publicly available at https://github.com/MengfeiD/O3N.
title O3N: Omnidirectional Open-Vocabulary Occupancy Prediction
topic Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
url https://arxiv.org/abs/2603.12144