基于约束重加权深度矩阵分解的多旋转平均
Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization
AI总结：
针对传统多旋转平均方法依赖人工噪声假设、现有学习类方法需标注的问题，提出结合深度矩阵分解、生成树边过滤、重加权及动态深度选择的无监督方法，兼具优化与学习类方法优势，经多数据集验证有效。
摘要：
多旋转平均在计算机视觉和机器人领域发挥着关键作用。传统基于优化的方法依据特定噪声假设优化非线性代价函数，而多数已有的基于学习的方法在监督训练过程中需要真实标签。考虑到人工设定的噪声假设未必在所有真实场景中都合理，本文提出了一种有效的旋转平均方法，以学习方式挖掘数据模式，同时无需标签。具体而言，我们采用深度矩阵分解，在无约束线性空间中直接求解多旋转平均问题。针对深度矩阵分解，我们设计了一种显式低秩且对称的神经网络模型，以更好地适配多旋转平均的应用背景。同时，我们利用基于生成树的边过滤来抑制旋转异常值的影响。此外，我们还采用了重加权方案和动态深度选择策略，以进一步提升鲁棒性。我们的方法融合了基于优化和基于学习两类方法的优势。在多个数据集上的实验结果验证了所提方法的有效性。
英文摘要：
Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on certain noise assumptions, while most previous learning-based methods require ground truth labels in the supervised training process. Recognizing the handcrafted noise assumption may not be reasonable in all real-world scenarios, this paper proposes an effective rotation averaging method for mining data patterns in a learning manner while avoiding the requirement of labels. Specifically, we apply deep matrix factorization to directly solve the multiple rotation averaging problem in unconstrained linear space. For deep matrix factorization, we design a neural network model, which is explicitly low-rank and symmetric to better suit the background of multiple rotation averaging. Meanwhile, we utilize a spanning tree-based edge filtering to suppress the influence of rotation outliers. What's more, we also adopt a reweighting scheme and dynamic depth selection strategy to further improve the robustness. Our method synthesizes the merit of both optimization-based and learning-based methods. Experimental results on various datasets validate the effectiveness of our proposed method.
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。
