適応的メモリを備えた深層視覚オドメトリ
Deep Visual Odometry with Adaptive Memory
局所から大域までの情報を適応的に記憶するメモリモジュールと時空間アテンションによる再精緻化を組み合わせ、誤差蓄積を抑えた学習ベース視覚オドメトリ手法を提案した論文。
著者: Fei Xue, Xin Wang, Junqiu Wang, Hongbin Zha
分類: cs.RO
原文アブストラクト
We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image snippets, leading to severe error accumulation. Global information is crucial for alleviating accumulated errors. However, it is challenging to effectively preserve such information for end-to-end systems. To deal with this challenge, we design an adaptive memory module, which progressively and adaptively saves the information from local to global in a neural analogue of memory, enabling our system to process long-term dependency. Benefiting from global information in the memory, previous results are further refined by an additional refining module. With the guidance of previous outputs, we adopt a spatial-temporal attention to select features for each view based on the co-visibility in feature domain. Specifically, our architecture consisting of Tracking, Remembering and Refining modules works beyond tracking. Experiments on the KITTI and TUM-RGBD datasets demonstrate that our approach outperforms state-of-the-art methods by large margins and produces competitive results against classic approaches in regular scenes. Moreover, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic algorithms tend to fail.
