Better match 3D point clouds having partial overlap using task-specific features with EDFNet
Better match 3D point clouds having partial overlap using task-specific features with EDFNet
Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds
arXiv paper abstract https://arxiv.org/abs/2210.14899v1
arXiv PDF paper https://arxiv.org/pdf/2210.14899v1.pdf
Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible.
However, the matching task aims at describing the corresponding points consistently across different 3D point clouds.
... propose to learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference.
... First, ... augment the matchability of correspondences by utilizing their repetitive local structure
... Second, ... propose a dynamical fusion module to jointly use different scale features ... analyze the consistency of them to judge the clean ones and perform larger aggregation weights on them during fusion
... Extensive evaluations validate that EDFNet learns a task-specific descriptor, which achieves state-of-the-art or comparable performance for robust matching of 3D point clouds.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
#ComputerVision #3D #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning
Comments