Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning

  • André O. Françani ITA
  • R. O. A. Marcos Maximo ITA

Resumo


Deep learning algorithms have driven expressive progress in many complex tasks. The loss function is a core component of deep learning techniques, guiding the learning process of neural networks. This paper contributes by introducing a consistency loss for visual odometry with deep learning-based approaches. The motion consistency loss explores repeated motions that appear in consecutive overlapped video clips. Experimental results show that our approach increased the performance of a model on the KITTI odometry benchmark.
Palavras-chave: deep learning, loss function, transformer, monocular visual odometry
Publicado
09/10/2023
FRANÇANI, André O.; MAXIMO, R. O. A. Marcos. Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning. In: SIMPÓSIO BRASILEIRO DE ROBÓTICA E SIMPÓSIO LATINO AMERICANO DE ROBÓTICA (SBR/LARS), 15. , 2023, Salvador/BA. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 409-414.