外观
论文arXiv 2609.291571 个月前
OREN-X：用于实时多模态建图的八叉树残差网络
原文链接：OREN-X: Octree Residual Network for Real-Time Multi-Modal Mapping（arXiv 2609.29157 · 发布日期：2026-09-24）
OREN-X: Octree Residual Network for Real-Time Multi-Modal Mapping
OREN-X用八叉树共享多模态场，统一几何、辐射与视觉语言在线建图，并在Replica上验证实时性与精度提升。
核心要点
- 长时通用自主需要多类空间信息，分开表示会增加内存和计算成本。
- 方法以3D八叉树共享索引多模态场，统一存取几何、辐射与视觉语言信息。
- 跨模态协同锐化SDF，在线字典学习压缩视觉语言特征并提高查询准确率。
- Replica上实时建图，SDF精度升33%，3D mIoU升71%、准确率升61%。
验证范围与局限：验证范围为Replica上的建图实验。
英文摘要 (Abstract)
To achieve general-purpose autonomy over long horizons, a robot needs to maintain spatial environment information that supports a variety of tasks: geometry for planning and control, radiance for rendering and relocalization, and vision-language features for open-vocabulary grounding. Existing methods represent and estimate each modality separately, multiplying memory and compute cost while forgoing potential synergy among the representations. We develop OREN-X, an online mapping method that uses an octree in 3D space as a shared data structure for indexing and storing a multi-modal field, capturing geometric, radiance, and vision-language information. OREN-X provides efficient unified storage and retrieval of these data in explicit/implicit and full/compressed form. Our unified representation yields cross-modality synergy: SDF estimates are sharpened by occupancy and radiance, while GPU-based ray-octree traversal and octree query enable real-time rendering. We also use online dictionary learning to compress the vision-language features, shrinking them 3.7x below full per-vertex storage while raising the query accuracy. On Replica, OREN-X maps in real time (80+ fps for SDF and 30+ fps for all four modalities), improves near-surface SDF accuracy by 33% over single-modality baselines, and improves mean open-vocabulary 3D mIoU by 71% and mean accuracy by 61% over the best prior method.
作者：Zhirui Dai, Qihao Qian, Dinh Minh Nguyen, Quan-Dung Pham, Kiana Bronder, Carlos Nieto-Granda, Yiyu Chen, Quan Nguyen, Nikolay Atanasov
来源
本页事实对应的公开页面，以原文为准。