Differences

This shows you the differences between two versions of the page.

publications:personal_photo_enhancement [2011/03/10 15:29]
elmer
publications:personal_photo_enhancement [2011/03/10 15:34] (current)
elmer
Line 1: Line 1:
====== Personal Photo Enhancement Using Example Images ====== ====== Personal Photo Enhancement Using Example Images ======
-==== Ce Liu, Lavanya Sharan, Edward H. Adelson, and Ruth Rosenholtz ====+==== Neel Joshi, Wojceich Matusik, Edward H. Adelson and David J. Kriegman ====
===== Abstract ===== ===== Abstract =====
-We are interested in identifying the material category, +We describe a framework for improving the quality of personal photos by using a person’s favorite photographs as examples. We observe that the majority of a person’s photographs include the faces of a photographer’s family and friends and often the errors in these photographs are the most disconcerting. We focus on correcting these types of images and use common faces across images to automatically perform both global and face-specific corrections. Our system achieves this by using face detection to align faces between “good” and “bad” photos such that properties of the good examples can be used to correct a bad photo. These “personal” photos provide strong guidance for a number of operations and, as a result, enable a number of high-quality image processing operations. We illustrate the power and generality of our approach by presenting a novel deblurring algorithm, and we show corrections that perform sharpening, superresolution, in-painting of over- and underexposured regions, and white-balancing.
-e.g. glass, metal, fabric, plastic or wood, from a single image +
-of a surface. Unlike other visual recognition tasks in +
-computer vision, it is difficult to find good, reliable features +
-that can tell material categories apart. Our strategy is to +
-use a rich set of low and mid-level features that capture various +
-aspects of material appearance. We propose an augmented +
-Latent Dirichlet Allocation (aLDA) model to combine +
-these features under a Bayesian generative framework +
-and learn an optimal combination of features. Experimental +
-results show that our system performs material recognition +
-reasonably well on a challenging material database, +
-outperforming state-of-the-art material/texture recognition +
-systems.+
===== Information ===== ===== Information =====
Line 25: Line 12:
---- dataentry pubitem ---- ---- dataentry pubitem ----
title       : Personal Photo Enhancement Using Example Images title       : Personal Photo Enhancement Using Example Images
-authors     : Ce Liu, Lavanya Sharan, Edward H. Adelson, and Ruth Rosenholtz +authors     : Neel Joshi, Wojceich Matusik, Edward H. Adelson and David J. Kriegman 
-citation    : EEE Conference on Computer Vision and Pattern Recognition (CVPR) pp239 - 246 +citation    : ACM Transactions on Graphics, 29(2
-shortcite   : CVPR 2010+shortcite   : ACM 2010
year        : 2010 year        : 2010
created_dt  : 2010-01-01 created_dt  : 2010-01-01
-keyword_tags: adelson, rosenholtz+keyword_tags: adelson
summary_page : publications:personal_photo_enhancement summary_page : publications:personal_photo_enhancement
pdf_url     : http://persci.mit.edu/pub_pdfs/personal_photo_enhancement.pdf pdf_url     : http://persci.mit.edu/pub_pdfs/personal_photo_enhancement.pdf
 
publications/personal_photo_enhancement.1299788982.txt.gz · Last modified: 2011/03/10 15:29 by elmer