Image enhancement and denoising by complex diffusion processes

By Guy Gilboa, Nir A. Sochen, Yehoshua Y. Zeevi. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004

485 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Segmentation-Free Dynamic Scene Deblurring (2014, background): “By contrast, without knowing the specific type of motion blur, traditional deterministic filter-based approaches can handle various types of blur [1, 7], but these filters are incapable of handling large motion blur and are sensitive to noise.”
Fields of Experts (2009, background): “There have been variational and diffusion-related approaches that try to overcome some of these limitations (Gilboa et al. 2004; Trobin et al. 2008).”
A Combined First and Second Order Variational Approach for Image Reconstruction (2012, unknown): “In TV2 the regulariser—regarded as a convex simplification of the Euler’s elastica idea—it has the ability to connect large gaps and the slight blur that is produced can be reduced by using a shock filter see for example [2, 45] and Fig.”
Graph spectral image smoothing using the heat kernel (2008, methodology): “Both our method and the aforementioned filters, i.e. RPM [7], NCRD [14], CED [11], TV [55], and WAVELET [56], were applied to the sequence of noisy images.”