Visual Place Recognition in Forests with Depth-Aware Distillation
It addresses the challenge of robust place recognition in natural forest environments for robotics and autonomous navigation.
The paper proposes a lightweight depth-aware distillation framework to inject geometric cues into a DINOv2-based model for visual place recognition in forests, achieving gains over an appearance-only counterpart on the WildCross benchmark.
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.