Sciweavers

Share
CVPR
2012
IEEE
7 years 9 months ago
Example-based cross-modal denoising
Widespread current cameras are part of multisensory systems with an integrated computer (smartphones). Computer vision thus starts evolving to cross-modal sensing, where vision an...
Dana Segev, Yoav Y. Schechner, Michael Elad
CVPR
2012
IEEE
7 years 9 months ago
A closed-form solution to uncalibrated photometric stereo via diffuse maxima
In this paper we propose a novel solution to uncalibrated photometric stereo. Our approach is to eliminate the socalled generalized bas relief (GBR) ambiguity by exploiting points...
Paolo Favaro, Thoma Papadhimitri
CVPR
2012
IEEE
7 years 9 months ago
Boosting bottom-up and top-down visual features for saliency estimation
Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. ...
Ali Borji
CVPR
2012
IEEE
7 years 9 months ago
Articulated people detection and pose estimation: Reshaping the future
State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured v...
Leonid Pishchulin, Arjun Jain, Mykhaylo Andriluka,...
CVPR
2012
IEEE
7 years 9 months ago
Background segmentation with feedback: The Pixel-Based Adaptive Segmenter
In this paper we present a novel method for foreground segmentation. Our proposed approach follows a nonparametric background modeling paradigm, thus the background is modeled by ...
Martin Hofmann 0011, Philipp Tiefenbacher, Gerhard...
CVPR
2012
IEEE
7 years 9 months ago
Synthesizing oil painting surface geometry from a single photograph
We present an approach to synthesize the subtle 3D relief and texture of oil painting brush strokes from a single photograph. This task is unique from traditional synthesize algor...
Wei Luo, Zheng Lu, Xiaogang Wang, Ying-Qing Xu, Mo...
CVPR
2012
IEEE
7 years 9 months ago
Recognizing proxemics in personal photos
Proxemics is the study of how people interact. We present a computational formulation of visual proxemics by attempting to label each pair of people in an image with a subset of p...
Yi Yang, Simon Baker, Anitha Kannan, Deva Ramanan
CVPR
2012
IEEE
7 years 9 months ago
3D Constrained Local Model for rigid and non-rigid facial tracking
We present 3D Constrained Local Model (CLM-Z) for robust facial feature tracking under varying pose. Our approach integrates both depth and intensity information in a common frame...
Tadas Baltrusaitis, Peter Robinson, Louis-Philippe...
CVPR
2012
IEEE
7 years 9 months ago
From pixels to physics: Probabilistic color de-rendering
Consumer digital cameras use tone-mapping to produce compact, narrow-gamut images that are nonetheless visually pleasing. In doing so, they discard or distort substantial radiomet...
Ying Xiong, Kate Saenko, Trevor Darrell, Todd Zick...
CVPR
2012
IEEE
7 years 9 months ago
Robust non-rigid registration of 2D and 3D graphs
We present a new approach to matching graphs embedded in R2 or R3 . Unlike earlier methods, our approach does not rely on the similarity of local appearance features, does not req...
Eduard Serradell, Przemyslaw Glowacki, Jan Kybic, ...
books