LiePoseNet: Heterogeneous Loss Function Based on Lie Group for Significant Speed-up of PoseNet Training Process

Autor:	Kurenkov, Mikhail, Kalinov, Ivan, Tsetserukou, Dzmitry
Rok vydání:	2022
Předmět:	Computer Science - Robotics 68T40
Druh dokumentu:	Working Paper
Popis:	Visual localization is an essential modern technology for robotics and computer vision. Popular approaches for solving this task are image-based methods. Nowadays, these methods have low accuracy and a long training time. The reasons are the lack of rigid-body and projective geometry awareness, landmark symmetry, and homogeneous error assumption. We propose a heterogeneous loss function based on concentrated Gaussian distribution with the Lie group to overcome these difficulties. Following our experiment, the proposed method allows us to speed up the training process significantly (from 300 to 10 epochs) with acceptable error values. Comment: 6 pages, 5 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2211.08480 Zobrazit plný text záznamu View this record from Arxiv