Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction.
Daniel GehrigMichelle RüeggMathias GehrigJavier Hidalgo-CarrióDavide ScaramuzzaPublished in: CoRR (2021)
Keyphrases
- prediction accuracy
- depth cues
- depth ordering
- neural network ensemble
- pose estimation
- recurrent networks
- three dimensional
- depth perception
- network structure
- event detection
- feed forward
- recurrent neural networks
- prediction model
- ego motion
- interesting events
- social networks
- depth information
- image sequences
- multimedia
- prediction error
- depth images
- spiking neural networks
- frame rate
- temporal information
- video frames
- multi modal