Abstract. Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods. Our taxonomy is designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. We have also produced several new multi-frame stereo data sets with ground truth and are making both the code and data sets available on the Web. Finally, we include a comparative evaluation of a large set of today’s best-performing stereo algorithms.

We propose a flexible new technique to easily calibrate a camera. It only requires the camera to observe a planar pattern shown at a few (at least two) different orientations. Either the camera or the planar pattern can be freely moved. The motion need not be known. Radial lens distortion is modeled. The proposed procedure consists of a closed-form solution, followed by a nonlinear refinement based on the maximum likelihood criterion. Both computer simulation and real data have been used to test the proposed technique, and very good results have been obtained. Compared with classical techniques which use expensive equipment such as two or three orthogonal planes, the proposed technique is easy to use and flexible. It advances 3D computer vision one step from laboratory environments to real world use. The corresponding software is available from the author’s Web page.

Realism in computer-generated images requires accurate input models for lighting, textures and BRDFs. One of the best ways of obtaining high-quality data is through measurements of scene attributes from real photographs by inverse rendering. However, inverse rendering methods have been largely limited to settings with highly controlled lighting. One of the reasons for this is the lack of a coherent mathematical framework for inverse rendering under general illumination conditions. Our main contribution is the introduction of a signal-processing framework which describes the reflected light field as a convolution of the lighting and BRDF, and expresses it mathematically as a product of spherical harmonic coefficients of the BRDF and the lighting. Inverse rendering can then be viewed as deconvolution. We apply this theory to a variety of problems in inverse rendering, explaining a number of previous empirical results. We will show why certain problems are ill-posed or numerically ill-conditioned, and why other problems are more amenable to solution. The theory developed here also leads to new practical representations and algorithms. For instance, we present a method to factor the lighting and BRDF from a small number of views, i.e. to estimate both simultaneously when neither is known.

We present a generative model for isotropic bidirectional reflectance distribution functions (BRDFs) based on acquired reflectance data. Instead of using analytical reflectance models, we represent each BRDF as a dense set of measurements. This allows us to interpolate and extrapolate in the space of acquired BRDFs to create new BRDFs. We treat each acquired BRDF as a single high-dimensional vector taken from a space of all possible BRDFs. We apply both linear (subspace) and non-linear (manifold) dimensionality reduction tools in an effort to discover a lowerdimensional representation that characterizes our measurements. We let users define perceptually meaningful parametrization directions to navigate in the reduced-dimension BRDF space. On the low-dimensional manifold, movement along these directions produces novel but valid BRDFs.

this article will be published in Presence, Vol

Many applications require tracking of complex 3D objects. These include visual servoing of robotic arms on specific target objects, Augmented Reality systems that require real-time registration of the object to be augmented, and head tracking systems that sophisticated interfaces can use. Computer Vision offers solutions that are cheap, practical and non-invasive. This survey reviews the different techniques and approaches that have been developed by industry and research. First, important mathematical tools are introduced: Camera representation, robust estimation and uncertainty estimation. Then a comprehensive study is given of the numerous approaches developed by the Augmented Reality and Robotics communities, beginning with those that are based on point or planar fiducial marks and moving on to those that avoid the need to engineer the environment by relying on natural features such as edges, texture or interest. Recent advances that avoid manual initialization and failures due to fast motion are also presented. The survery concludes with the different possible choices that should be made when implementing a 3D tracking system and a discussion of the future of vision-based 3D tracking. Because it encompasses many computer vision techniques from lowlevel vision to 3D geometry and includes a comprehensive study of the massive literature on the subject, this survey should be the handbook of the student, the researcher, or the engineer who wants to implement a 3D tracking system. 1

This paper describes the use of task primitives in robot learning from observation. A framework has been developed that uses observed data to initially learn a task and then the agent goes on to increase its performance through repeated task performance (learning from practice). Data that is collected while a human performs a task is parsed into small parts of the task called primitives. Modules are created for each primitive that encode the movements required during the performance of the primitive, and when and where the primitives are performed. The feasibility of this method is currently being tested with agents that learn to play a virtual and an actual air hockey game. 1

We present the design and implementation of a real-time, distributed light field camera. Our system allows multiple viewers to navigate virtual cameras in a dynamically changing light field that is captured in real-time. Our light field camera consists of 64 commodity video cameras that are connected to off-the-shelf computers. We employ a distributed rendering algorithm that allows us to overcome the data bandwidth problems inherent in dynamic light fields. Our algorithm works by selectively transmitting only those portions of the video streams that contribute to the desired virtual views. This technique not only reduces the total bandwidth, but it also allows us to scale the number of cameras in our system without increasing network bandwidth. We demonstrate our system with a number of examples.

Sentient Computing provides computers with perception so that they can react and provide assistance to user activities. Physical spaces are made sentient when they are wired with networks of sensors capturing context data, which is communicated to computing devices spread through the environment. These devices interpret the information provided and react by performing the actions expected by the user. Among the types of context information provided by sensors, location has proven to be especially useful. Since location is an important context that changes whenever the user moves, a reliable location-tracking system is critical to many sentient applications. However, the sensor technologies used in indoor location tracking are expensive and complex to deploy, configure and maintain. These factors have prevented a wider adoption of Sentient Computing in our living and working spaces. This paper presents TRIP, a low-cost and easily deployable vision-based sensor technology addressing these issues. TRIP employs off-the-shelf hardware (low-cost CCD cameras and PCs) and printable 2-D circular markers for entity identification and location. The usability of TRIP is illustrated through the implementation of several sentient applications.

We describe a dataset of several thousand calibrated, time-stamped, geo-referenced, high dynamic range color images, acquired under uncontrolled, variable illumination conditions in an outdoor region spanning several hundred meters. The image data is grouped into several regions which have little mutual inter-visibility. For each group, the calibration data is globally consistent on average to roughly five centimeters and 0.1 # , or about four pixels of epipolar registration. All image, feature and calibration data is available for interactive inspection and downloading at http://city.lcs.mit.edu/data.