DytanVO：动态环境下视觉里程计与运动分割的联合优化
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments
AI总结：
针对动态环境下视觉里程计易失效的问题，提出DytanVO框架，联合优化相机自运动与运动分割，在真实动态场景中ATE较现有最优VO方法提升27.7%，泛化性良好。
摘要：
基于学习的视觉里程计（VO）算法得益于高容量模型和海量标注数据，在常见静态场景下性能优异，但在动态、人员密集的环境中往往失效。语义分割常被用于在估计相机运动前剔除动态关联，但代价是会丢失静态特征，且难以扩展到未见过的类别。本文利用相机自运动与运动分割之间的相互依赖关系，证明二者可在单个基于学习的框架中联合优化。具体而言，我们提出DytanVO，这是首个针对动态环境的监督学习型VO方法。它实时接收连续两帧单目图像，以迭代方式预测相机自运动。在真实动态环境中，我们的方法相较于现有最优VO方案，在绝对轨迹误差（ATE）上平均提升27.7%，甚至与在后端优化轨迹的动态视觉SLAM系统相比性能也颇具竞争力。在大量未见环境中的实验也证明了本方法的泛化能力。
英文摘要：
Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments. Semantic segmentation is largely used to discard dynamic associations before estimating camera motions but at the cost of discarding static features and is hard to scale up to unseen categories. In this paper, we leverage the mutual dependence between camera ego-motion and motion segmentation and show that both can be jointly refined in a single learning-based framework. In particular, we present DytanVO, the first supervised learning-based VO method that deals with dynamic environments. It takes two consecutive monocular frames in real-time and predicts camera ego-motion in an iterative fashion. Our method achieves an average improvement of 27.7% in ATE over state-of-the-art VO solutions in real-world dynamic environments, and even performs competitively among dynamic visual SLAM systems which optimize the trajectory on the backend. Experiments on plentiful unseen environments also demonstrate our method's generalizability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
