EV-MGRFlowNet: Motion-Guided Recurrent Network for Unsupervised Event-Based Optical Flow With Hybrid Motion-Compensation Loss.
Hao ZhuangZheng FangXinjie HuangKuanxu HouDelei KongChenming HuPublished in: IEEE Trans. Instrum. Meas. (2024)
Keyphrases
- motion compensation
- motion field
- optical flow
- motion estimation
- recurrent networks
- motion compensated
- motion vectors
- block matching
- optical flow estimation
- video coding
- motion model
- video compression
- image sequences
- motion estimation algorithm
- video super resolution
- recurrent neural networks
- flow field
- motion segmentation
- motion parameters
- biologically inspired
- block matching algorithm
- camera motion
- velocity field
- vector field
- beating heart
- motion estimates
- ego motion
- inter frame
- rigid motion
- neural network
- feature tracking
- video coder
- moving camera
- interpolation filter
- dense motion field
- feed forward
- global motion
- multi frame
- motion analysis
- machine learning