Unsupervised Learning of the Total Variation Flow. (arXiv:2206.04406v1 [cs.CV])

The total variation (TV) flow generates a scale-space representation of an
image based on the TV functional. This gradient flow observes desirable
features for images such as sharp edges and enables spectral, scale, and
texture analysis. The standard numerical approach for TV flow requires solving
multiple non-smooth optimisation problems. Even with state-of-the-art convex
optimisation techniques, this is often prohibitively expensive and strongly
motivates the use of alternative, faster approaches. Inspired by and extending
the framework of physics-informed neural networks (PINNs), …

arxiv cv flow learning unsupervised unsupervised learning