In this paper, we address the problem of synthesizing novel views from a set of input images. State of the art methods, such as the Unstructured Lumigraph, have been using heuristics to combine information from the original views, often using an explicit or implicit approximation of the scene geometry. While the proposed heuristics have been largely explored and proven to work effectively, a Bayesian formulation was recently introduced, formalizing some of the previously proposed heuristics, pointing out which physical phenomena could lie behind each. However, some important heuristics were still not taken into account and lack proper formalization. We contribute a new physics-based generative model and the corresponding Maximum a Posteriori estimate, providing the desired unification between heuristics-based methods and a Bayesian formulation. The key point is to systematically consider the error induced by the uncertainty in the geometric proxy. We provide an extensive discussion, analyzing how the obtained equations explain the heuristics developed in previous methods. Furthermore, we show that our novel Bayesian model significantly improves the quality of novel views, in particular if the scene geometry estimate is inaccurate.

We address the topic of novel view synthesis from a stereoscopic pair of images. The techniques have mainly 3 stages: the reconstruction of correspondences between the views, the estimation of the blending factor of each view for the final view, and the rendering. The state of the art has mainly focused on the correspondence topic, but little work addresses the question of which blending factors are best. The rendering methods can be classified into “direct” methods, defining the final image as a function of the original images, and “vari-ational” methods, where the synthesized image is expressed as the solution minimising an energy. In this paper, we experiment different combinations of the blending factors and the rendering method, in order to demonstrate the effect of these two factors on the final image quality.

The scene flow describes the 3D motion of every point in a scene between two time steps. We present a novel method to estimate a dense scene flow using intensity and depth data. It is well known that local methods are more robust under noise while global techniques yield dense motion estimation. We combine local and global constraints to solve for the scene flow in a variational framework. An adaptive TV (Total Variation) regularization is used to preserve motion discontinuities. Besides, we constrain the motion using a set of 3D correspondences to deal with large displacements. In the experimentation our approach outperforms previous scene flow from intensity and depth methods in terms of accuracy.

The 3-D shape perceived from viewing a stereoscopic movie depends on the viewing conditions, most notably on the screen size and distance, and depth and size distortions appear because of the differences between the shooting and viewing geometries. When the shooting geometry is constrained, or when the same stereoscopic movie must be displayed with different viewing geometries (e.g. in a movie theater and on a 3DTV), these depth distortions may be reduced by new view synthesis techniques. They usually involve three steps: computing the stereo disparity, computing a disparity-dependent 2-D mapping from the original stereo pair to the synthesized views, and finally composing the synthesized views. In this paper, we compare different disparity-dependent mappings in terms of perceived shape distortion and alteration of the images, and we propose a hybrid mapping which does not distort depth and minimizes modifications of the image content.

This paper presents a method for scene flow estimation from a calibrated stereo image sequence. The scene flow contains the 3-D displacement field of scene points, so that the 2-D optical flow can be seen as a projection of the scene flow onto the images. We propose to recover the scene flow by coupling the optical flow estimation in both cameras with dense stereo matching between the images, thus reducing the number of unknowns per image point. The use of a variational framework allows us to properly handle discontinuities in the observed surfaces and in the 3-D displacement field. Moreover our approach handles occlusions both for the optical flow and the stereo. We obtain a partial differential equations system coupling both the optical flow and the stereo, which is numerically solved using an original multi- resolution algorithm. Whereas previous variational methods were estimating the 3-D reconstruction at time t and the scene flow separately, our method jointly estimates both in a single optimization. We present numerical results on synthetic data with ground truth information, and we also compare the accuracy of the scene flow projected in one camera with a state-of-the-art single-camera optical flow computation method. Results are also presented on a real stereo sequence with large motion and stereo discontinuities. Source code and sample data are available for the evaluation of the algorithm.

Scene flow represents the 3-D motion of points in the scene, just as optical flow is related to their 2-D motion in the images. As opposed to classical methods which compute scene flow from optical flow, we propose to compute it by tracking 3-D points and surface elements (surfels) in a multi-camera setup (at least two cameras are needed). Two methods are proposed: in the first one, the translation of each 3-D point is found by matching the neighborhoods of its 2-D projections in each camera between two time steps; in the second one, the full pose of a surfel is recovered by matching the image of its projection with a texture template attached to the surfel, and visibility changes caused by occlusion or rotation of surfels are handled. Both methods detect lost or untrackable points and surfels. They were designed for real-time execution and can be used for fast extraction of scene flow from multi-camera sequences.

A three-dimensional (3-D) method for tracking the coronary arteries through a temporal sequence of biplane X-ray angiography images is presented. A 3-D centerline model of the coronary vasculature is reconstructed from a biplane image pair at one time frame, and its motion is tracked using a coarse-to-fine hierarchy of motion models. Three-dimensional constraints on the length of the arteries and on the spatial regularity of the motion field are used to overcome limitations of classical two-dimensional vessel tracking methods, such as tracking vessels through projective occlusions. This algorithm was clinically validated in five patients by tracking the motion of the left coronary tree over one cardiac cycle. The root mean square reprojection errors were found to be submillimeter in 93% (54/58) of the image pairs. The performance of the tracking algorithm was quantified in three dimensions using a deforming vascular phantom. RMS 3-D distance errors were computed between centerline models tracked in the X-ray images and gold-standard centerline models of the phantom generated from a gated 3-D magnetic resonance image acquisition. The mean error was 0.69 (+/- 0.06) mm over eight temporal phases and four different biplane orientations.

We present a system for modeling buildings from a single correlation-based digital elevation model (DEM). The model is constructed in two stages. The first stage segments the DEM into planar surface patches that describe the building. The second stage generates the final polygonal model of the building using weak geometric constraints. We use robust estimation methods at different stages of our modeling process to develop an efficient and noise-insensitive modeling system. The proposed system is fully automatic and does not use any a priori information about the shape of the buildings. We present results on isolated buildings and on a large area of the city of Berlin.

We present in this article a system which improves a digital elevation model (DEM). The method reconstructs all the facades of the building and then, corrects the initial DEM by deleting the points of the roofs which pass over the boundaries defined by the facades. We correct the shapes of the buildings with the initial photographs to have sharp contours. The proposed approach does not use any a priori information about the orientation of the facades and the shape of the buildings. We present results with synthetic and real images.

To make a Euclidean reconstruction of the world seen through a stereo rig, we can either use a calibration grid, and the results will rely on the precision Of the grid and the extracted points of interest, or use self-calibration. Past work on self-calibration is focussed on the use of only one camera, and gives sometimes very unstable results. In this paper, we use a stereo rig which is supposed to be weakly calibrated using a method such as the one described in Deriche et al. (1994). Then, by matching two sets of points of the same scene reconstructed from different points of view, we try to find both the homography that maps the projective reconstruction to the Euclidean space and the displacement from the first set of points to the second set of points. We present results of the Euclidean reconstruction of a whole object from uncalibrated cameras using the method proposed here.

We are considering the problem of recovering the three-dimensional geometry of a scene from binocular stereo disparity. Once a dense disparity map has been computed from a stereo pair of images, one often needs to calculate some local differential properties of the corresponding 3-D surface such as orientation or curvatures. The usual approach is to build a 3-D reconstruction of the surface(s) from which all shape properties will then be derived without ever going back to the original images. In this paper, we depart from this paradigm and propose to use the images directly to compute the shape properties. We thus propose a new method extending the classical correlation method to estimate accurately both the disparity and its derivatives directly from the image data. We then relate those derivatives to differential properties of the surface such as orientation and curvatures.>