用ORB特征引导自监督里程计，提升精度与跨场景适应能力
ORB-SfMLearner: ORB-Guided Self-supervised Visual Odometry with Selective Online Adaptation
- 用ORB特征指导深度网络进行位姿估计，增强鲁棒性
- 在KITTI和vKITTI上优于当前最先进方法，位姿误差更低
- 支持选择性在线适配，快速适应新环境，适合实际部署
深度视觉里程计尽管研究广泛，但仍存在精度不足和泛化能力差的问题，限制了其广泛应用。为此，我们提出一种基于定向FAST与旋转BRIEF（ORB）特征引导的自监督视觉里程计方法，名为ORB-SfMLearner。通过创新性地利用ORB特征进行学习型自身运动估计，显著提升了结果的鲁棒性和准确性。我们引入交叉注意力机制以增强PoseNet的可解释性，并发现车辆行驶方向可通过注意力权重有效解释。为提升泛化能力，提出的有选择性的在线适配策略使网络能快速、精准地调整至不同场景下的最优参数。在KITTI和vKITTI数据集上的实验结果表明，该方法在自身运动估计精度和泛化性能上均超越现有最先进深度视觉里程计方法。代码已开源：https://github.com/PeaceNeil/ORB-SfMLearner。
原文摘要 · Abstract (English)
Deep visual odometry, despite extensive research, still faces limitations in accuracy and generalizability that prevent its broader application. To address these challenges, we propose an Oriented FAST and Rotated BRIEF (ORB)-guided visual odometry with selective online adaptation named ORB-SfMLearner. We present a novel use of ORB features for learning-based ego-motion estimation, leading to more robust and accurate results. We also introduce the cross-attention mechanism to enhance the explainability of PoseNet and have revealed that driving direction of the vehicle can be explained through the attention weights. To improve generalizability, our selective online adaptation allows the network to rapidly and selectively adjust to the optimal parameters across different domains. Experimental results on KITTI and vKITTI datasets show that our method outperforms previous state-of-the-art deep visual odometry methods in terms of ego-motion accuracy and generalizability. Code is available at https://github.com/PeaceNeil/ORB-SfMLearner
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。