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....

Additional results on real scenes We show four additional scenes captured by the Nexus5 cellphone camera in Figure A1 and seven scenes captured by the Samsung S3 cellphone camera in Figure A2. Among the seven Samsung scenes, three of them already appeared in [9]. Here we also show flow field estimations in addition to the depth map estimations. The scene, camera and imaging conditions of all ou...

In this paper, we describe a multi-depth camera system for 3D video contents generation. We combine five video cameras and five TOF depth cameras to capture a scene in real time. By taking advantages of both active and passive sensor based depth acquisition methods, we can estimate multi-view depth sequences accurately. After performing several steps of preprocessing, the depth sequences are wa...

Scene’s 3D modelling, gesture recognition and motion tracking are fields in rapid and continuous development which have caused growing demand on interactivity in video-game and e-entertainment market. Starting from the idea of creating a sensor that allows users to play without having to hold any remote controller, the Microsoft Kinect device was created. The Kinect has always attract researche...

How good are cheap depth cameras, namely the Microsoft Kinect, compared to state of the art Time-ofFlight depth cameras? In this paper several depth cameras of different types were put to the test on a variety of tasks in order to judge their respective performance and to find out their weaknesses. We will concentrate on the common area of applications for which both types are specified, i.e. n...

We present a novel algorithm for image-based surface reconstruction from a set of calibrated images. The problem is formulated in Bayesian framework, where estimates of depth and visibility in a set of selected cameras are iteratively improved. The core of the algorithm is the minimisation of overall geometric L2 error between measured 3D points and the depth estimates. In the visibility estima...

The work at hand presents a method to assess the quality of human sleep within a non-laboratory environment. The monitoring of patients is performed with a Kinect device, thus making the method non-invasive independent of immediate physical contact to subjects. The results of a study carried out as proof of concept are discussed and compared with the polysomnography-based gold standard of sleep...

We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frameto-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. Given a sequence of frames, SfM-Net predicts depth, segmentation, camera and rigid object motions, converts those into a dense frame-to-frame motion field (optical flow), differe...

In this paper, we present a new image based rendering technology called panoramic mosaics of slit images with depth. By limit camera motion only in a horizontal plane, a slit image with united depth value is used as the element of rendering. Compared with panorama, this method can support the movement of virtual camera. Multiple panoramic mosaics of slit images with depth can be joined up to pr...