We present a new structure from motion (Sfm) technique based on point and vanishing point (VP) matches in images. First, all global camera rotations are computed from VP matches as well as relative rotation estimates obtained from pairwise image matches. A new multi-staged linear technique is then used to estimate all camera translations and 3D points simultaneously. The proposed method involves first performing pairwise reconstructions, then robustly aligning these in pairs, and finally aligning all of them globally by simultaneously estimating their unknown relative scales and translations. In doing so, measurements inconsistent in three views are efficiently removed. Unlike sequential Sfm, the proposed method treats all images equally, is easy to parallelize and does not require intermediate bundle adjustments. There is also a reduction of drift and significant speedups up to two order of magnitude over sequential Sfm. We compare our method with a standard Sfm pipeline [1] and demonstrate that our linear estimates are accurate on a variety of datasets, and can serve as good initializations for final bundle adjustment. Because we exploit VPs when available, our approach is particularly well-suited to the reconstruction of man-made scenes.

In this paper, we present results and experiments with several methods for bundle adjustment, producing the fastest bundle adjuster ever published in terms of computation and convergence. From a computational perspective, the fastest methods naturally handle the block-sparse pattern that arises in a reduced camera system. Adapting to the naturally arising block-sparsity allows the use of BLAS3, efficient memory handling, fast variable ordering, and customized sparse solving, all simultaneously. We present two methods; one uses exact minimum degree ordering and block-based LDL solving and the other uses block-based preconditioned conjugate gradients. Both methods are performed on the reduced camera system. We show experimentally that the adaptation to the natural block sparsity allows both of these methods to perform better than previous methods. Further improvements in convergence speed are achieved by the novel use of embedded point iterations. Embedded point iterations take place inside each camera update step, yielding a greater cost decrease from each camera update step and, consequently, a lower minimum. This is especially true for points projecting far out on the flatter region of the robustifier. Intensive analyses from various angles demonstrate the improved performance of the presented bundler.

We present a technique for fast Poisson blending and gradient domain compositing. Instead of using a single piecewise-smooth offset map to perform the blending, we associate a separate map with each input source image. Each individual offset map is itself smoothly varying and can therefore be represented using a low-dimensional spline. The resulting linear system is much smaller than either the original Poisson system or the quadtree spline approximation of a single (unified) offset map. We demonstrate the speed and memory improvements available with our system and apply it to large panoramas. We also show how robustly modeling the multiplicative gain rather than the offset between overlapping images leads to improved results, and how adding a small amount of Laplacian pyramid blending improves the results in areas of inconsistent texture.

Most existing structure from motion (SFM) approaches for unordered images cannot handle multiple instances of the same structure in the scene. When image pairs containing different instances are matched based on visual similarity, the pairwise geometric relations as well as the correspondences inferred from such pairs are erroneous, which can lead to catastrophic failures in the reconstruction. In this paper, we investigate the geometric ambiguities caused by the presence of repeated or duplicate structures and show that to disambiguate between multiple hypotheses requires more than pure geometric reasoning. We couple an expectation maximization (EM)-based algorithm that estimates camera poses and identifies the false match-pairs with an efficient sampling method to discover plausible data association hypotheses. The sampling method is informed by geometric and image-based cues. Our algorithm usually recovers the correct data association, even in the presence of large numbers of false pairwise matches.

A ''Panoramic Viewfinder'' provides an intuitive interactive viewfinder display operating on a digital camera display screen. This interactive viewfinder provides real-time assistance in capturing images for constructing panoramic image mosaics. The Panoramic Viewfinder ''brushes'' a panorama from images captured in any order, while providing visual feedback to the user for ensuring that desired scene elements will appear in the final panorama. This visual feedback presents real-time stitched previews of the panorama while capturing images. In one embodiment, the viewfinder display of the Panoramic Viewfinder includes a ''mosaic preview'' which presents a stitched mosaic preview of the captured images; a live display window representing a ''current content'' of the camera viewfinder, which is mapped to a matching location within the mosaic preview; and an optional panoramic ''cropping frame'' overlaid onto the mosaic preview which illustrates a section of the mosaic which will survivea rectangular cropping of the mosaic.

View interpolation and image-based rendering algorithms often produce visual artifacts in regions where the 3D scene geometry is erroneous, uncertain, or incomplete. We introduce ambient point clouds constructed from colored pixels with uncertain depth, which help reduce these artifacts while providing non-photorealistic background coloring and emphasizing reconstructed 3D geometry. Ambient point clouds are created by randomly sampling colored points along the viewing rays associated with uncertain pixels. Our real-time rendering system combines these with more traditional rigid 3D point clouds and colored surface meshes obtained using multiview stereo. Our resulting system can handle larger-range view transitions with fewer visible artifacts than previous approaches.