Sciweavers

Share
ICCV
2011
IEEE
7 years 7 months ago
Object Recoloring based on Intrinsic Image Estimation
Object recoloring is one of the most popular photoediting tasks. The problem of object recoloring is highly under-constrained, and existing recoloring methods limit their applicat...
Shida Beigpour, Joost van de Weijer
ICCV
2011
IEEE
7 years 7 months ago
Adaptive Deconvolutional Networks for Mid and High Level Feature Learning
We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers ...
Matthew D. Zeiler, Graham W. Taylor, Rob Fergus
GBRPR
2011
Springer
7 years 10 months ago
Convexity Grouping of Salient Contours
Convexity represents an important principle of grouping in visual perceptual organization. This paper presents a new technique for contour grouping based on convexity and has the f...
Padraig Corcoran, Peter Mooney, James Tilton
CVPR
2011
IEEE
7 years 11 months ago
Internal Statistics of a Single Natural Image
Statistics of ‘natural images’ provides useful priors for solving under-constrained problems in Computer Vision. Such statistics is usually obtained from large collections of ...
Maria Zontak, Michal Irani
CVPR
2011
IEEE
8 years 4 months ago
Sparsity-based Image Denoising via Dictionary Learning and Structural Clustering
Where does the sparsity in image signals come from? Local and nonlocal image models have supplied complementary views toward the regularity in natural images the former attempts t...
Weisheng Dong, Xin Li
BMVC
2010
8 years 5 months ago
Back to the Future: Learning Shape Models from 3D CAD Data
Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of o...
Michael Stark, Michael Goesele, Bernt Schiele
TIP
2010
132views more  TIP 2010»
8 years 5 months ago
Compress Compound Images in H.264/MPGE-4 AVC by Exploiting Spatial Correlation
—Compound images are a combination of text, graphics and natural image. They present strong anisotropic features, especially on the text and graphics parts. These anisotropic fea...
Cuiling Lan, Guangming Shi, Feng Wu
PAMI
2007
148views more  PAMI 2007»
8 years 6 months ago
Infinitely Divisible Cascades to Model the Statistics of Natural Images
—We propose to model the statistics of natural images, thanks to the large class of stochastic processes called Infinitely Divisible Cascades (IDCs). IDCs were first introduced i...
Pierre Chainais
TIP
2002
99views more  TIP 2002»
8 years 6 months ago
Reconstructing images from their most singular fractal manifold
Real world images are complex objects, difficult to describe but at the same time possessing a high degree of redundancy. A very recent study [1] on the statistical properties of n...
Antonio Turiel, Angela del Pozo
IVC
2007
184views more  IVC 2007»
8 years 7 months ago
Image distance functions for manifold learning
Many natural image sets are samples of a low-dimensional manifold in the space of all possible images. When the image data set is not a linear combination of a small number of bas...
Richard Souvenir, Robert Pless
books