線を視覚的な文として扱う:視覚的自己位置推定のための文脈考慮型ライン記述子
Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization
線分を単語(点)からなる文とみなし、Transformerで可変長の線を扱うライン記述子を提案し、点と線を併用した自己位置推定で精度向上を示した論文。
著者: Sungho Yoon, Ayoung Kim
分類: cs.CV, cs.RO
原文アブストラクト
Along with feature points for image matching, line features provide additional constraints to solve visual geometric problems in robotics and computer vision (CV). Although recent convolutional neural network (CNN)-based line descriptors are promising for viewpoint changes or dynamic environments, we claim that the CNN architecture has innate disadvantages to abstract variable line length into the fixed-dimensional descriptor. In this paper, we effectively introduce Line-Transformers dealing with variable lines. Inspired by natural language processing (NLP) tasks where sentences can be understood and abstracted well in neural nets, we view a line segment as a sentence that contains points (words). By attending to well-describable points on aline dynamically, our descriptor performs excellently on variable line length. We also propose line signature networks sharing the line's geometric attributes to neighborhoods. Performing as group descriptors, the networks enhance line descriptors by understanding lines' relative geometries. Finally, we present the proposed line descriptor and matching in a Point and Line Localization (PL-Loc). We show that the visual localization with feature points can be improved using our line features. We validate the proposed method for homography estimation and visual localization.
