FractalPINN-Flow is a fractal-recursive unsupervised network trained with total variation regularization to estimate dense optical flow from image pairs.
Subspace correction methods for a class of nonsmooth and nonadditive convex variational problems with mixedL 1/L2 data-fidelity in image processing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
FractalPINN-Flow is a fractal-recursive unsupervised network trained with total variation regularization to estimate dense optical flow from image pairs.