2 papers
cs.CV2025
FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
Sara Behnamian, Rasoul Khaksarinezhad, Andreas Langer
We present FractalPINN-Flow, an unsupervised deep learning framework for dense optical flow estimation that learns directly from consecutive grayscale frames without requiring grou…
math.NA2024
DeepTV: A neural network approach for total variation minimization
Andreas Langer, Sara Behnamian
Neural network approaches have been demonstrated to work quite well to solve partial differential equations in practice. In this context approaches like physics-informed neural net…