Interplay between preconditioning and regularization for linear ill-posed problems solved by conjugate gradient. Application to optical flow estimation.
Ahmed ChabibJean-François WitzVincent MagnierPierre GosseletPublished in: CoRR (2024)
Keyphrases
- conjugate gradient
- conjugate gradient algorithm
- optical flow estimation
- optical flow computation
- optical flow
- levenberg marquardt
- training algorithm
- flow field
- reproducing kernel hilbert space
- motion field
- convergence rate
- neural network
- motion model
- markov random field
- faster convergence
- d objects
- artificial neural networks
- image sequences