The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We present a novel framework for estimating depth-map in a single 2D image. The proposed framework employs both vanishing point and superpixels as geometric and texture cues, respectively. The combination of both cues can generate a feasible perceptual depth-map, which will be applied to 2D to 3D image conversion.
In this paper, we propose a hole-filling based memory controller of a disparity modification system for multiview three-dimensional video. Three-dimensional video provides realistic perception and is one component of the next generation of video. The key technique for three-dimensional displays is accurate disparity recording and hole filling in multiview three-dimensional video. In order to solve...
Depth information is essential for 3DTV applications, as it is used for rendering in many modern 3D displays. In this paper, we propose a new approach for 3DTV content synthesis, by integrating an existing state-of-the-art MRF-based disparity estimation method with additional pre- and post-processing steps. The key of the proposed method is the decomposition of the scene in foreground and background...
Previous studies of depth and distance estimation with autostereoscopic 3D displays indicate the users do not necessarily exhibit better depth perception with such displays. Yet, users claim 3D displays provide higher immersiveness. As shapes of objects are often described by their angles, it is expected that angle perception would contribute to object recognition and scene understanding. However;...
Virtual view synthesis is an important technique for multi-view 3D display. This makes that multi-view images for 3D display can be created by only two-view images. An efficient virtual view synthesis method was proposed based on disparity map and image interpolation. An adaptive weight stereo matching approach was adopted to obtain the initial disparity map. Cross-checking technique was utilized...
This paper proposes an approach for 2D-to-3D conversion for multiview displays. It employs an object-based approach where objects at large depth differences are first segmented by semi-automatic tools. Appropriate depth values are assigned to these objects and the missing image pixels at the background are filled in by inpainting techniques so that different views of the image can be synthesized....
In the context of 3-D scene modeling, this work aims at the accurate estimation of the pose of a close-range 3-D modeling device, in real-time and passively from its own images. This novel development makes it possible to abandon using inconvenient, expensive external positioning systems. The approach comprises an ego-motion algorithm tracking natural, distinctive features, concurrently with customary...
A method for estimating temporally and spatially consistent dense depth maps in multiple camera setups is presented which is important for reduction of perception artifacts in 3D displays. For this purpose, initially, depth estimation is performed for each camera with the piece-wise planarity assumption and Markov Random Field (MRF) based relaxation at each time instant independently. During the relaxation...
We developed an FTV system to process, and display information of 3D scene in realtime, in which users freely control their own viewpoint/listening-point position. Free listening-point can be generated by either (i) ray-space representation of sound wave field (source sound independent), or (ii) by acoustic transfer function estimation (source sound dependent) and blind separation of sources of sounds...
Content generation is one of the most critical issues for the growth of 3DTV services in future. New autostereoscopic displays, such as the Philips Wowreg 3D display have significant advantages, including improved 3D viewing experience, wider viewing angles, multiple viewers and no need for special glasses. However, due to their content formatting requirements (2D + depth), live-action content is...
In multiview 3DTVs the original 3D-scene is reconstructed based on the corresponding pixels of adjacent 2D views. For conventional 2D display the highest image quality is usually achieved by uniform distribution of pixels. However, recent studies on the 3D reconstruction process show that for a given total resolution, a non-uniform horizontally-finer resolution yields better visual experience on 3D...
In this paper, a real-time augmented view synthesis system is proposed. With real-time consideration and augmented reality property, the proposed system provides a novel application for making car pillars transparent to enlarge the eyesight of the drivers. Thanks to the proposed trinocular depth estimation, online depth generation becomes possible through trinocular fast dense disparity estimation...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.