Method, system and computer program product for enhancing a depth map

摘要

A first depth map is generated in response to a stereoscopic image from a camera. The first depth map includes first pixels having valid depths and second pixels having invalid depths. In response to the first depth map, a second depth map is generated for replacing at least some of the second pixels with respective third pixels having valid depths. For generating the second depth map, a particular one of the third pixels is generated for replacing a particular one of the second pixels. For generating the particular third pixel, respective weight(s) is/are assigned to a selected one or more of the first pixels in response to value similarity and spatial proximity between the selected first pixel(s) and the particular second pixel. The particular third pixel is computed in response to the selected first pixel(s) and the weight(s).

主权项

1. A method performed by at least one device for enhancing a depth map, the method comprising:
generating a first depth map in response to a stereoscopic image from a camera, wherein the first depth map includes first pixels having valid depths and second pixels having invalid depths; and in response to the first depth map, generating a second depth map for replacing at least some of the second pixels with respective third pixels having valid depths, wherein generating the second depth map includes generating a particular one of the third pixels for replacing a particular one of the second pixels, and wherein generating the particular third pixel includes assigning respective weight(s) to a selected one or more of the first pixels in response to value similarity and spatial proximity between the selected first pixel(s) and the particular second pixel, and wherein generating the particular third pixel includes computing the particular third pixel in response to the selected first pixel(s) and the weight(s); wherein the stereoscopic image includes first and second images, and wherein generating the first depth map includes: generating a third depth map in response to the first image as a reference image and the second image as a non-reference image; generating a fourth depth map in response to the second image as the reference image and the first image as the non-reference image; and generating the first depth map in response to the third and fourth depth maps.