Self-supervised Vector-Quantization in Visual SLAM using Deep Convolutional Autoencoders.
Amir ZarringhalamSaeed Shiry GhidaryAli Mohades KhorasaniPublished in: CoRR (2022)
Keyphrases
- vector quantization
- visual slam
- deep belief networks
- deep learning
- restricted boltzmann machine
- unsupervised learning
- real time
- dynamic environments
- image compression
- generative model
- vector quantizer
- probabilistic model
- camera motion
- bundle adjustment
- sparse coding
- machine learning
- monocular camera
- distortion measure
- denoising
- simultaneous localization and mapping
- structure from motion
- learning algorithm
- face recognition
- multibody
- sparse representation
- neural network
- feature space
- object recognition
- image sequences