Nonlocal Similarity Image Filtering
Abstract: We exploit the recurrence of patches at different locations, orientations and scales in an image to perform denoising and interpolation. While previous methods based on “nonlocal filtering” identify corresponding patches only up to translations, we consider more general similarity transformations. Due to the additional computational burden, we break the problem down into two steps: First, we extract similarity invariant descriptors at each pixel location; second, we search for similar patches by matching descriptors. The descriptors used are inspired by SIFT features, whereas the similarity search is solved via the minimization of a cost function adapted from local denoising methods. Our method compares favorably with existing denoising and interpolation algorithms as tested on several datasets.
Paper: Yifei Lou, Paolo Favaro and Stefano Soatto, "Nonlocal Similarity Image Filtering," (PDF) In the proceeding of the International Conference on Image Analysis and Processing (ICIAP), 2009.
Talk: ICIAP, Salerno Italy, Sep. 9 2009
Abstact: Most algorithms for reconstructing shape from defocus assume that the images are obtained with a camera that has been previously calibrated so that the aperture, focal plane, and focal length are known. In this manuscript we characterize the set of scenes that can be reconstructed from defocused images regardless of calibration parameters. In lack of knowledge about the camera or about the scene, reconstruction is possible only up to an equivalence class that is described analytically. When weak knowledge about the scene is available, however, we show how it can be exploited in order to auto-calibrate the imaging device. This includes imaging a slanted plane or generic assumptions on the restoration of the deblurred images.
Paper: Yifei Lou, Paolo Favaro, Andrea Bertozzi and Stefano Soatto, "Autocalibration and Uncalibrated Reconstruction of Shape from Defocus," IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2007 (PDF)
Talk: IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis (MN), June 21, 2007
Image recovery via Nonlocal Operators
Abstract: This paper considers two nonlocal regularizations for image recovery, which exploit the spatial interactions in images. We get superior results using preprocessed data as input for the weighted functionals. Applications discussed include image deconvolution and tomographic reconstruction. The numerical results show our method outperforms some previous ones.
Paper: Yifei Lou, Xiaoqun Zhang, Stanley Osher and Andrea Bertozzi, "Image Recovery via Nonlocal Operators," submitted to Journal of Scientific Computing. CAM report 08-35
Talk: SIAM Conference on Imaging Sciences, San Diego (CA), July 8, 2008
Abstact: We study a model of the shape, motion and appearance of a scene that captures occlusions, deformations and changes in its radiance. This
model is based on a collection of overlapping layers, each of which can move and deform with an intensity function that can change over time. We discuss the generality of this model in relations to existing ones such as optical flow, motion segmentation and inpainting, etc. We illustrate the model on synthetic image sequences to show its performance on those special cases.
A summer project. Click to see the poster.
Direct Sparse Deblurring
Abstract: We propose a deblurring algorithm that explicitly takes into account the sparse characteristics of natural images and does not entail solving a numerically ill-conditioned backward-diffusion.The key observation is that the sparse coefficients that encode a given image with respect to an over- complete basis are the same that encode a blurred version of the image with respect to a modified basis. Following an ``analysis-by-synthesis'' approach, an explicit generative model is used to compute a sparse representation of the blurred image, and the coefficients of which are used to combine elements of the original basis to yield a restored image. We compare our algorithm against the state of the art in variational methods as well as wavelet-based algorithms.
Paper: Yifei Lou, Andrea Bertozzi and Stefano Soatto, "Direct Sparse Deblurring," submitted to Journal of Mathematical Imaging and Vision, CAM report 09-15
Burst Denoising
Abstract: Taking photographs under low light conditions with a hand-held camera is problematic. A long exposure time can cause motion blur due to the camera shaking and a short exposure time gives a noisy image. We consider the new technical possibility offered by cameras that take image bursts. Each image of the burst is sharp but noisy. In this preliminary investigation, we explore a strategy to effciently denoise multi-images or video. The proposed algorithm is a complex image processing chain involving accurate registration, video equalization, noise estimation and the use of state-of-the-art denoising methods. Yet, we show that this complex chain may become risk free thanks to a key feature: the noise model can be estimated accurately from the image burst. Preliminary tests will be presented. On the technical side, the method can already be used to estimate a non parametric camera noise model from any image burst.
Paper: Toni Buades, Yifei Lou, J.M. Morel and Zhongwei Tang, "A Note on multi-image denoising" (PDF), In the proceeding of the International Workshop on Local and Non-Local Approximation (LNLA) in Image Processing, 2009.
Talk: LNLA, Tuusula Finland, Aug. 19, 2009
Online Demo is under construction. link
