Sciweavers

CVPR
2011
IEEE
13 years 7 months ago
Piecing Together the Segmentation Jigsaw using Context
We present an approach to jointly solve the segmentation and recognition problem using a multiple segmentation framework. We formulate the problem as segment selection from a pool...
Xi Chen, Arpit Jain, Abhinav Gupta, Larry Davis
CVPR
2011
IEEE
13 years 7 months ago
Noise Suppression in Low-Light Images through Joint Denoising and Demosaicing
We address the effects of noise in low-light images in this paper. Color images are usually captured by a sensor with a color filter array (CFA). This requires a demosaicing proc...
Priyam Chatterjee, Neel Joshi, Sing Bing Kang, Yas...
CVPR
2011
IEEE
13 years 7 months ago
Recovering Shape from a Single Image of a Mirrored Surface from Curvature Constraints
This paper presents models and algorithms for estimating the shape of a mirrored surface from a single image of that surface, rendered under an unknown, natural illumination. Whil...
Marshall Tappen
CVPR
2011
IEEE
13 years 7 months ago
Energy Based Multiple Model Fitting for Non-Rigid Structure from Motion
In this paper we reformulate the 3D reconstruction of deformable surfaces from monocular video sequences as a labeling problem. We solve simultaneously for the assignment of featu...
Chris Russell, Joao Fayad, Lourdes Agapito
CVPR
2011
IEEE
13 years 7 months ago
Learning a Blind Measure of Perceptual Image Quality
It is often desirable to evaluate an image based on its quality. For many computer vision applications, a perceptually meaningful measure is the most relevant for evaluation; howe...
Huixuan Tang, Neel Joshi, Ashish Kapoor
CVPR
2011
IEEE
13 years 7 months ago
Global Stereo Matching Leveraged by Sparse Ground Control Points
We present a novel global stereo model that makes use of constraints from points with known depths, i.e., the Ground Control Points (GCPs) as referred to in stereo literature. Our...
Liang Wang, Ruigang Yang
CVPR
2011
IEEE
13 years 7 months ago
Shape Estimation in Natural Illumination
The traditional shape-from-shading problem, with a single light source and Lambertian reflectance, is challenging since the constraints implied by the illumination are not suffi...
Micah Johnson, Edward Adelson
CVPR
2011
IEEE
13 years 7 months ago
Learning to Find Occlusion Regions
For two consecutive frames in a video, we identify which pixels in the first frame become occluded in the second. Such general-purpose detection of occlusion regions is difficul...
Ahmad Humayun, Oisin Mac Aodha, Gabriel Brostow
CVPR
2011
IEEE
13 years 7 months ago
Relative pose problem for non-overlapping surveillance cameras with known gravity vector
We present a method for estimating the relative pose of two calibrated or uncalibrated non-overlapping surveillance cameras from observing a moving object. We show how to tackle t...
Branislav Micusik