Generating a depth map from a two-dimensional source image for stereoscopic and multiview imaging
Abstract
Depth maps are generated from a monoscopic source images and asymmetrically smoothed to a near-saturation level. Each depth map contains depth values focused on edges of local regions in the source image. Each edge is defined by a predetermined image parameter having an estimated value exceeding a predefined threshold. The depth values are based on the corresponding estimated values of the image parameter. The depth map is used to process the source image by a depth image based rendering algorithm to create at least one deviated image, which forms with the source image a set of monoscopic images. At least one stereoscopic image pair is selected from such a set for use in generating different viewpoints for multiview and stereoscopic purposes, including still and moving images.
Claims
exact text as granted — not AI-modified1 - 20 . (canceled)
21 . A method for generating a smoothed depth map associated with a monoscopic source image, comprising:
(a) obtaining a depth map for the monoscopic source image; and (b) smoothing the depth map to a near-saturation level around an area corresponding to at least one local region of the monoscopic source image, said area including a change in depth exceeding a predefined threshold, so as to minimize dis-occlusions around said area in a newly-rendered image generated based on the smoothed depth map, wherein range or strength of the smoothing are substantially greater in the vertical than the horizontal orientation.
22 . The method of claim 21 , wherein step (b) is performed using a smoothing filter.
23 . The method of claim 22 , wherein the smoothing filter comprises a Gaussian filter.
24 . The method of claim 21 , wherein step (b) comprises smoothing the entire depth map.
25 . The method of claim 21 , further comprising applying a depth image based rendering (DIBR) algorithm to the depth map and the monoscopic source image to obtain one or more deviated images for forming at least one stereoscopic image pair.
26 . The method of claim 25 , further comprising displaying the at least one stereoscopic image pair on a 3D display.
27 . The method of claim 21 , wherein the depth map is derived from one or more monoscopic images.
28 . The method of claim 21 , wherein the depth map is derived based on the monoscopic source image.
29 . The method of claim 21 , wherein the depth map is obtained by an image capturing device.
30 . The method of 27 , where the depth map is a sparse depth map derived from a raw depth map using the steps of:
identifying a subset of the array of pixels representing an edge of the at least one local region of the raw depth map; and assigning to each pixel within said subset, a depth value based on the corresponding estimated value of the image parameter.
31 . An apparatus comprising a depth map smoother configured to implement the method of claim 21 .
32 . The apparatus of claim 31 , wherein the depth map smoother comprises an asymmetric smoothing filter for asymmetrically smoothing the depth map in both the vertical and horizontal directions to obtain the smoothed depth map, wherein range or strength of the smoothing are substantially greater in the vertical than the horizontal orientation.
33 . The apparatus of claim 31 further comprising a depth image based rendering (DIBR) processor for processing the monoscopic source image (MSI) associated with the depth map using the smoothed depth map to render at least one deviated image to form at least one stereoscopic image pair.
34 . The apparatus of claim 33 further comprising a 3D display for generating at least one stereoscopic view from the at least one stereoscopic image pair.
35 . The method of claim 21 , wherein both the range and strength of the smoothing are substantially greater in the vertical than the horizontal orientation.Join the waitlist — get patent alerts
Track US2013009952A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.