LiftFeat: 3D幾何情報を考慮した局所特徴マッチング
LiftFeat: 3D Geometry-Aware Local Feature Matching
単眼深度推定から得た表面法線を教師信号として3D幾何特徴を抽出し、2D記述子と融合することで、厳しい照明変化や低テクスチャ環境でも頑健な軽量特徴マッチング手法を提案した。
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: Yepeng Liu, Wenpeng Lai, Zhou Zhao, Yuxuan Xiong, Jinchi Zhu, Jun Cheng, Yongchao Xu
分類: cs.CV, cs.RO
原文アブストラクト
Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in scenarios with drastic lighting changes, low texture areas, or repetitive patterns. In this paper, we propose a new lightweight network called \textit{LiftFeat}, which lifts the robustness of raw descriptor by aggregating 3D geometric feature. Specifically, we first adopt a pre-trained monocular depth estimation model to generate pseudo surface normal label, supervising the extraction of 3D geometric feature in terms of predicted surface normal. We then design a 3D geometry-aware feature lifting module to fuse surface normal feature with raw 2D descriptor feature. Integrating such 3D geometric feature enhances the discriminative ability of 2D feature description in extreme conditions. Extensive experimental results on relative pose estimation, homography estimation, and visual localization tasks, demonstrate that our LiftFeat outperforms some lightweight state-of-the-art methods. Code will be released at : https://github.com/lyp-deeplearning/LiftFeat.
