Minisymposium on Locally Adaptive Patch-based Image and Video Restoration


The past few years have witnessed the emergence of a series of papers that tackle various image processing tasks in a locally adaptive, patch-based manner. These methods serve various applications, such as denoising and deblurring of still images and video, inpainting, image decomposition, segmentation, super-resolution reconstruction, compression, and more. As the name suggests, these techniques operate locally in the image, applying the same process for every pixel by manipulating small patches of pixels. As such, these methods are typically simple, highly parallelizable. Remarkably, in most cases, the proposed algorithms are leading to state-of-the-art results. In this minisyposium we bring gather the leading researchers in this emerging arena to present a series of talks that will expose the current state of knowledge in this field.


Michael Elad (Technion, Israel)

Peyman Milanfar (University of California, Santa Cruz)


Part I:

Monday, July 7, 2008










10:30-10:55 Multidimensional Kernel Regression for Video Processing and Reconstruction

Hiroyuki Takeda and Peyman Milanfar, University of California, Santa Cruz; Matan Protter and Michael Elad, Technion, Israel; Peter van Beek, Sharp Labs of America

Related Papers:

H. Takeda, and P. Milanfar, M. Protter, M. Elad, “Superresolution Without Explicit Subpixel Motion Estimation ”, Submitted to IEEE Trans. Image Processing

H. Takeda, P. van Beek, and P. Milanfar, “Spatio-Temporal Video Interpolation and Denoising Using Motion-Assisted Steering Kernel (MASK) Regression”, Proceedings of IEEE International Conference on Image Processing (ICIP), San Diego, CA, October 2008.

11:00-11:25 A Discriminative Approach for Transform Based Restoration

Yacov Hel-Or, The Interdisciplinary Center, Israel; Doron Shaked, HP Laboratories, Israel

Related Paper:

Y. Hel-Or and D. Shaked, "A Discriminative approach for Wavelet Shrinkage Denoising" IEEE Trans. on Image Processing, Vol 17, No. 4, April 2008

11:30-11:55 Image Super-Resolution via Sparse Representation

Jianchao Yang, John Wright, and Yi Ma, University of Illinois at Urbana-Champaign

Related Paper:

Jianchao Yang, John Wright, and Yi Ma, "Image Super-Resolution as Sparse Representation of Raw Image Patches", CVPR, 2008, Anchorage, Alaska

12:00-12:25 Image Processing with Manifold Models

Gabriel Peyre, Ceremade, France

12:30-12:55 Learning to Classify

Guillermo Sapiro, University of Minnesota, Minneapolis


Part II:

Wednesday, July 9, 2008















10:30-10:55 Generalizing the Non-Local-Means to Super-Resolution-Reconstruction of Image Sequences

Michael Elad and Matan Protter, Technion, Israel; Hiro Takeda and Peyman Milanfar, University of California, Santa Cruz

Related Paper:

M. Protter, M. Elad, H. Takeda, and P. Milanfar, “Generalizing the Non-Local-Means to Super-resolution Reconstruction ”, accepted for publication in IEEE Trans. Image Processing, April 2008

11:00-11:25 Fast Super-Resolution of Video Sequences using Sparse Directional Transforms

Sandeep Kanumuri and Onur Guleryuz, DoCoMo Communications Laboratories

Related paper:

Sandeep Kanumuri, Onur G. Guleryuz, and M. Reha Civanlar, "Sparse directional transforms for superresolution reconstruction of mobile video," Proc. SPIE Conf. on Applications of Digital Image Processing XXX, San Diego, Aug. 2007.

11:30-11:55 Bayesian Non-local Means, Image Redundancy and Adaptive Estimation for Image Representation and Applications

Charles Kervrann, IRISA, France; Patrick Perez, IRISA-INRIA, France; Jerome Boulanger, Institut Curie, France

Related Papers:

J. Boulanger, Ch. Kervrann, J. Salamero, J.-B. Sibarita, P. Bouthemy "Non-parametric regression for patch-based fluorescence microscopy image sequence denoisng" Rapport de recherche INRIA, No 6651, Septembre 2008

12:00-12:25 Adaptive Non-local Transforms for Image/video Denoising, Restoration, and Enhancement, and for Compressive Sensing Image Reconstruction

Alessandro Foi, Kostadin Dabov, Aram Danielyan, Karen Egiazarian and Vladimir Katkovnik, Tampere University of Technology, Finland

Related Links:

back to top

Last Updated December 2, 2008

free invisible hit counter