that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties. We apply the algorithm to image segmentation using two different kinds of local neighborhoods in constructing the graph, and illustrate the results with both real and synthetic images. The algorithm

While different optical flow techniques continue to appear, there has been a lack of quantitative evaluation of existing methods. For a common set of real and synthetic image sequences, we report the results of a number of regularly cited optical flow techniques, including instances of differential

velocity of the brightness pattern varies smoothly almost everywhere in the image. An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences. The algorithm is robust in that it can handle image sequences that are quantized rather coarsely

We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler

We show a learning-based method for low-level vision problems. We set-up a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently

We present a method that uses measured scene radiance and global illumination in order to add new objects to light-based models with correct lighting. The methodusesahighdynamicrangeimagebasedmodelofthescene, ratherthansyntheticlightsources,toilluminatethe new objects. Tocomputetheillumination,thesceneis consideredasthreecomponents:thedistantscene, the localscene, andthesyntheticobjects. The distant scene is assumed tobephotometricallyunaffectedbytheobjects, obviatingtheneedforreflectancemodelinformation. Thelocalsceneisendowedwithestimatedreflectancemodel informationsothatitcancatchshadows andreceivereflectedlightfromthenewobjects. Renderings are createdwithastandardglobalilluminationmethodby simulating theinteractionoflightamongstthethreecomponents. A differentialrenderingtechniqueallowsforgoodresults to be obtained when only an estimate ofthelocalscenereflectancepropertiesisknown. Weapplythegeneralmethodtotheproblemofrendering syntheticobjectsintorealscenes. The light-based model is constructed from an approximategeometricmodelofthesceneandbyusinga lightprobetomeasuretheincidentilluminationatthe locationof thesyntheticobjects. Theglobalilluminationsolutionisthen compositedintoaphotographofthesceneusing thedifferentialrenderingtechnique. Weconcludebydiscussingtherelevance of the technique to recovering surface reflectance properties in uncontrolled lighting situations. Applications of the method include visual effects, interior design, and architectural visualization.

This paper discusses a new method for capturing the complete appearanceof both synthetic and real world objects and scenes, representing this information, and then using this representation to render images of the object from new camera positions. Unlike the shape capture process traditionally used

the object has all coefficients nonzero, but the coefficients obey an `p bound, for some p ∈ (0, 1]. These experiments show that the basic inequalities behind the CS method seem to involve reasonable constants. We next consider synthetic examples modelling problems in spectroscopy and image pro-

is flexible and can work with any pursuit method (e.g., basis pursuit, FOCUSS, or matching pursuit). We analyze this algorithm and demonstrate its results both on synthetic tests and in applications on real image data.

Distance learning and virtual laboratory applications have motivated the use of inexpensive visual stereo solutions for computer displays. The anaglyph method is such a solution. Several techniques have been proposed for the production of anaglyphs. We discuss three approaches: the Photoshop algorithm and its variants, the least squares algorithm proposed by Eric Dubois that optimizes in the CIE color space, and the midpoint algorithm that minimizes the sum of the distances between the anagylph color and the left and right eye colors in CIEL*a*b*. Our results show that each method has its advantages and disadvantages in faithful color representation and in stereo quality as it relates to region merging and ghosting.