制約付き再重み付け深層行列分解による複数回転平均化
Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization
ラベル不要の深層行列分解で複数回転平均化を解き、スパニングツリーによる外れ値除去と再重み付けでロバスト性を高めた手法を提案。
著者: Shiqi Li, Jihua Zhu, Yifan Xie, Naiwen Hu, Mingchen Zhu, Zhongyu Li, Di Wang
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
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.
