Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2010-12-15
Computer Science
Computer Vision and Pattern Recognition
Submitted to IJCV. Conference version presented at ACCV 2010
Scientific paper
In this paper, we show how to efficiently and effectively extract a class of "low-rank textures" in a 3D scene from 2D images despite significant corruptions and warping. The low-rank textures capture geometrically meaningful structures in an image, which encompass conventional local features such as edges and corners as well as all kinds of regular, symmetric patterns ubiquitous in urban environments and man-made objects. Our approach to finding these low-rank textures leverages the recent breakthroughs in convex optimization that enable robust recovery of a high-dimensional low-rank matrix despite gross sparse errors. In the case of planar regions with significant affine or projective deformation, our method can accurately recover both the intrinsic low-rank texture and the precise domain transformation, and hence the 3D geometry and appearance of the planar regions. Extensive experimental results demonstrate that this new technique works effectively for many regular and near-regular patterns or objects that are approximately low-rank, such as symmetrical patterns, building facades, printed texts, and human faces.
Ganesh Arvind
Liang Xi Xia
Ma Yi
Zhang Zhengdong
No associations
LandOfFree
TILT: Transform Invariant Low-rank Textures does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with TILT: Transform Invariant Low-rank Textures, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and TILT: Transform Invariant Low-rank Textures will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-13258