The iframe on this page is empty and contains no contentSkip to content

Dr Dragotti



Image Restoration and Image Super-Resolution

Leveraging from the theory of sparse signal representation and sparse sampling (RecoSamp) we develop registration algorithms that can register accurately regions of an image using only a very small number of features. Given a set of well registered images we then perform super-resolution using appropriate sparsity priors. There are many different image models available that lead to sparse representation. The one we use assumes that the signal is well approximated by a piecewise polynomial image. This model is ideal for depth images but is also suitable for most natural images. Our approximation is calculated using a quadtree decomposition to adaptively partition the image. This approach leads to state of the art super-resolution algorithms and to state-of-the art image denoising algorithms for very noisy images.


Image Restoration Results:


 noisy
 denoised
 denoised2

Noisy Image
 Denoised with our method
 Denoised with  alternative method


Image Super-Resolution Results:

Original Low-resolution super-resolved image
Original (2014x3039)
 Roi (128x128)
 super-res (1024 x1024)




Main publications:

Research Areas

Wavelet theory.
Sampling theory.
Image and video processing and compression.
Image Based Rendering and Image Super-Resolution.
Social Bookmarking:
Delicious
Digg