UniLoc用单一模态实现通用定位，支持语言、图像、点云任意输入。
UniLoc: Towards Universal Place Recognition Using Any Single Modality
- 通过层级匹配机制，融合实例与场景级特征进行定位。
- 在KITTI-360上跨模态表现更优，单模态也具竞争力。
- 提出SAP模块，动态加权实例描述子以生成场景表示。
目前大多数定位方法聚焦于单模态检索，虽在特定环境中表现良好，但跨模态方法更具灵活性，可无缝切换地图与查询来源，并通过统一模型降低计算开销，提升样本效率。本文提出通用定位方案UniLoc，支持任意单模态输入（自然语言、图像或点云）。UniLoc利用大规模对比学习进展，在两个层次上进行层级匹配：实例级匹配与场景级匹配。特别地，提出一种基于自注意力的池化（SAP）模块，评估实例描述子在聚合为场景描述子时的重要性。在KITTI-360数据集上的实验表明，跨模态设置下性能显著提升，单模态场景下也达到竞争性结果。
原文摘要 · Abstract (English)
To date, most place recognition methods focus on single-modality retrieval. While they perform well in specific environments, cross-modal methods offer greater flexibility by allowing seamless switching between map and query sources. It also promises to reduce computation requirements by having a unified model, and achieving greater sample efficiency by sharing parameters. In this work, we develop a universal solution to place recognition, UniLoc, that works with any single query modality (natural language, image, or point cloud). UniLoc leverages recent advances in large-scale contrastive learning, and learns by matching hierarchically at two levels: instance-level matching and scene-level matching. Specifically, we propose a novel Self-Attention based Pooling (SAP) module to evaluate the importance of instance descriptors when aggregated into a place-level descriptor. Experiments on the KITTI-360 dataset demonstrate the benefits of cross-modality for place recognition, achieving superior performance in cross-modal settings and competitive results also for uni-modal scenarios. Our project page is publicly available at https://yan-xia.github.io/projects/UniLoc/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。