用深度信息增强视觉定位，提升森林环境下的识别鲁棒性。
Visual Place Recognition in Forests with Depth-Aware Distillation
- 通过深度感知蒸馏，将几何信息融入DINOv2模型
- 在WildCross数据集上显著提升对外观变化的适应能力
- 适合需要高鲁棒性的野外导航系统研究者
自然森林环境中视觉位置识别仍面临挑战，主要由于植被重复、结构线索弱以及不同遍历间的显著外观差异。本文提出一种轻量级深度感知蒸馏框架，将几何信息注入基于DINOv2的位置识别模型，同时保持其预训练特征空间不变。在最新提出的WildCross基准测试中，该方法相比仅依赖外观的基线模型取得性能提升，展现出对外观变化的强鲁棒性。结果表明，深度作为重要补充模态，在自然环境中的位置识别中具有关键作用，深度感知蒸馏为更鲁棒的森林感知提供了有前景的方向。
原文摘要 · Abstract (English)
Visual place recognition in natural forest environments remains challenging due to repetitive vegetation, weak structural cues, and significant appearance variation across traversals. To address this limitation, this paper proposes a lightweight depth-aware distillation framework that injects geometric cues into a DINOv2-based place recognition model, while maintaining its pre-trained descriptor space. Evaluated on the recent WildCross benchmark, the proposed approach yields gains over an appearance-only counterpart, providing robustness to appearance variations. These results demonstrate the importance of depth as a strong complementary modality for place recognition in natural environments and identify depth-aware distillation as a promising direction for more robust forest perception.
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。