A method to restore the depth map of an RGB-D image using smooth depth neighborhood (SDN) supports is presented. The SDN supports are computed based on the corresponding color image of the depth map. Compared with the most widely used square supports, the proposed SDN supports can well-capture the local structure of the object. Only pixels with similar depth values are allowed to be included in...

In this paper, we propose a new refinement filter for depth maps. The filter convolutes a depth map by a jointly computed kernel on a natural image with a weight map. We call the filter weighted joint bilateral filter. The filter fits an outline of an object in the depth map to the outline of the object in the natural image, and it reduces noises. An additional filter of slope depth compensatio...

0167-8655/$ see front matter 2012 Elsevier B.V. A http://dx.doi.org/10.1016/j.patrec.2012.06.003 ⇑ Corresponding author. E-mail addresses: [email protected] (F. Qi), gmshi@x 1 Principal corresponding author. Depth acquisition becomes inexpensive after the revolutionary invention of Kinect. For computer vision applications, depth maps captured by Kinect require additional processing to fill up mi...

This paper presents a system for refining the accuracy and realism of coarse piecewise planar models from an uncalibrated sequence of images. First, dense depth maps are estimated by aligning a planar region of a scene in each image, approximating camera calibration, and generating dense planar parallax. These depth maps are then robustly fused to obtain incrementally refined surface estimates....

This paper presents a bijection between combinatorial maps and a class of enriched trees, corresponding to a class of expression trees in some logical systems (constrained lambda terms). Starting from two alternative definitions of combinatorial maps: the classical definition by gluing halfedges, and a definition by non-ambiguous depth-first traversal, we derive non-trivial asymptotic expansion...

A 3D object–based depth estimation approach from stereoscopic image sequences is presented in this paper that introduces a memory for depth information from preceding image pairs. This approach is used in the EU–RACE project DISTIMA for applications like remote handling, quality control and TV post processing. Compared to depth estimation approaches that compute depth maps from consecutive ster...

This paper proposes a novel architecture for video-rate stereo machine. It is unfeasible to directly implement a video-rate machine with occlusion handling mechanism, because the computational cost for the correspondence search is higher than that of a simple polynocular stereo algorithm without occlusion handling. Our idea is to integrate two algorithms withlwithout occlusion handling mechanis...

This contribution gives an overview of automatic 3D scene reconstruction and visualisation from uncalibrated and handheld camera image sequences. We address specifically the problems that are associated with calibration and visual-geometric reconstruction of complex scenes with occlusions and view-dependent surfaces. The scene is then represented by large sets of calibrated real viewpoints with...