Showing papers by "Shai Avidan published in 2013"

FasT-Match: Fast Affine Template Matching

Abstract: Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure. There is a huge number of transformations to consider but we prove that they can be sampled using a density that depends on the smoothness of the image. For each potential transformation, we approximate the SAD error using a sub linear algorithm that randomly examines only a small number of pixels. We further accelerate the algorithm using a branch-and-bound scheme. As images are known to be piecewise smooth, the result is a practical affine template matching algorithm with approximation guarantees, that takes a few seconds to run on a standard machine. We perform several experiments on three different datasets, and report very good results. To the best of our knowledge, this is the first template matching algorithm which is guaranteed to handle arbitrary 2D affine transformations.

Stereo Seam Carving a Geometrically Consistent Approach

Abstract: Image retargeting algorithms attempt to adapt the image content to the screen without distorting the important objects in the scene. Existing methods address retargeting of a single image. In this paper, we propose a novel method for retargeting a pair of stereo images. Naively retargeting each image independently will distort the geometric structure and hence will impair the perception of the 3D structure of the scene. We show how to extend a single image seam carving to work on a pair of images. Our method minimizes the visual distortion in each of the images as well as the depth distortion. A key property of the proposed method is that it takes into account the visibility relations between pixels in the image pair (occluded and occluding pixels). As a result, our method guarantees, as we formally prove, that the retargeted pair is geometrically consistent with a feasible 3D scene, similar to the original one. Hence, the retargeted stereo pair can be viewed on a stereoscopic display or further processed by any computer vision algorithm. We demonstrate our method on a number of challenging indoor and outdoor stereo images.

Multiple histogram matching

Abstract: Histogram Matching (HM) is a common technique for finding a monotonic map between two histograms. However, HM cannot deal with cases where a single mapping is sought between two sets of histograms. This paper presents a novel technique that finds such a mapping in an optimal manner under various histograms distance measures.

Space-Time Tradeoffs in Photo Sequencing

Abstract: Photo-sequencing is the problem of recovering the temporal order of a set of still images of a dynamic event, taken asynchronously by a set of uncalibrated cameras. Solving this problem is a first, crucial step for analyzing (or visualizing) the dynamic content of the scene captured by a large number of freely moving spectators. We propose a geometric based solution, followed by rank aggregation to the photo-sequencing problem. Our algorithm trades spatial certainty for temporal certainty. Whereas the previous solution proposed by [4] relies on two images taken from the same static camera to eliminate uncertainty in space, we drop the static-camera assumption and replace it with temporal information available from images taken from the same (moving) camera. Our method thus overcomes the limitation of the static-camera assumption, and scales much better with the duration of the event and the spread of cameras in space. We present successful results on challenging real data sets and large scale synthetic data (250 images).

DCSH - Matching Patches in RGBD Images

Abstract: We extend patch based methods to work on patches in 3D space. We start with Coherency Sensitive Hashing (CSH), which is an algorithm for matching patches between two RGB images, and extend it to work with RGBD images. This is done by warping all 3D patches to a common virtual plane in which CSH is performed. To avoid noise due to warping of patches of various normals and depths, we estimate a group of dominant planes and compute CSH on each plane separately, before merging the matching patches. The result is DCSH - an algorithm that matches world (3D) patches in order to guide the search for image plane matches. An independent contribution is an extension of CSH, which we term Social-CSH. It allows a major speedup of the k nearest neighbor (kNN) version of CSH - its runtime growing linearly, rather than quadratic ally, in k. Social-CSH is used as a subcomponent of DCSH when many NNs are required, as in the case of image denoising. We show the benefits of using depth information to image reconstruction and image denoising, demonstrated on several RGBD images.

Incremental Level Set Tracking

Abstract: We consider the problem of contour tracking in the level set framework. Level set methods rely on low level image features, and very mild assumptions on the shape of the object to be tracked. To improve their robustness to noise and occlusion, one might consider adding shape priors that give additional weight to contours that are more likely than others. This works well in practice, but assumes that the class of object to be tracked is known in advance so that the proper shape prior is learned. In this work we propose to learn the shape priors on the fly. That is, during tracking we learn an eigenspace of the shape contour and use it to detect and handle occlusions and noise. Experiments on a number of sequences reveal the advantages of our method.