次元削減を正則化として用いたネットワークベース相対姿勢回帰の汎化性能向上
Improving the generalization of network based relative pose regression: dimension reduction as a regularizer
学習可能なマッチング層と次元正則化を導入し、画像特徴量に依存しない姿勢回帰を実現することで、未知シーンや大きな視点変化に対する汎化性能とロバスト性を向上させた研究。
著者: Xiaqing Ding, Yue Wang, Li Tang, Yanmei Jiao, Rong Xiong
分類: cs.CV, cs.RO
原文アブストラクト
Visual localization occupies an important position in many areas such as Augmented Reality, robotics and 3D reconstruction. The state-of-the-art visual localization methods perform pose estimation using geometry based solver within the RANSAC framework. However, these methods require accurate pixel-level matching at high image resolution, which is hard to satisfy under significant changes from appearance, dynamics or perspective of view. End-to-end learning based regression networks provide a solution to circumvent the requirement for precise pixel-level correspondences, but demonstrate poor performance towards cross-scene generalization. In this paper, we explicitly add a learnable matching layer within the network to isolate the pose regression solver from the absolute image feature values, and apply dimension regularization on both the correlation feature channel and the image scale to further improve performance towards generalization and large viewpoint change. We implement this dimension regularization strategy within a two-layer pyramid based framework to regress the localization results from coarse to fine. In addition, the depth information is fused for absolute translational scale recovery. Through experiments on real world RGBD datasets we validate the effectiveness of our design in terms of improving both generalization performance and robustness towards viewpoint change, and also show the potential of regression based visual localization networks towards challenging occasions that are difficult for geometry based visual localization methods.
