Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization

10 Sep 2021  ยท  Sungho Yoon, Ayoung Kim ยท

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Homography Estimation Oxford and Paris LT AUC@5px 29.5 # 2
AUC@10px 52.1 # 1
AUC@20px 69.4 # 1
P 57.7 # 1
R 61.5 # 1
F 59.5 # 1
Homography Estimation Oxford and Paris SOLD2 AUC@5px 31.8 # 1
AUC@10px 51.5 # 2
AUC@20px 67.1 # 2
P 41.1 # 2
R 45.8 # 2
F 43.3 # 2

Methods


No methods listed for this paper. Add relevant methods here