CVPRApr, 2023
通过联合学习检测和描述关键点来增强可变形局部特征
Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypoints
Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. Nascimento
TL;DRDALF is a new, deformation-aware network for jointly detecting and describing keypoints, which can be used for local feature extraction in computer vision and delivers better performance when dealing with matching deformable surfaces.