Fast Anisotropic Smoothing of Multi-Valued Images using Curvature-Preserving PDE's
By David Tschumperlé. International Journal of Computer Vision, 2006
312 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/aa56a6186bb9ef8747cf593e15d27e19781ca23c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Edwin Robert Hancock
- Christine M. Guillemot
- O. Le Meur
- Fan Zhang
- Pierre Vandergheynst
- Luc Van Gool
- Antonio Torralba
- Chen Change Loy
Citations in the corpus
- Graph spectral image smoothing using the heat kernel (2008, background): “Although the curvaturepreserving PDE [58] works fairly well and is able to eliminate severe noise, it has a tendency to over smooth and blur the fine details of the objects.”
- Image Inpainting : Overview and Recent Advances (2014, methodology): “It was observed in [11] that Gaussian behavior inherent to the use of tensors for defining orientation and strength of the diffusion degrades the reconstruction of curved image structures such as corners.”