深度認識蒸留による森林環境での視覚的位置認識
Visual Place Recognition in Forests with Depth-Aware Distillation
森林環境での視覚的位置認識の課題に対し、DINOv2ベースのモデルに幾何学的手がかりを注入する軽量な深度認識蒸留フレームワークを提案し、WildCrossベンチマークで外観変動に対する頑健性を向上させた。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Walter Nedov, Saimunur Rahman, Kavindie Katuwandeniya, David Hall, Kaushik Roy, Peyman Moghadam
分類: cs.CV, cs.RO
原文アブストラクト
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.
