Virtual viewpoint image generation process on basis of depth map segmentation and rendering

A virtual viewpoint and depth map technology, applied in the field of virtual viewpoint image generation, can solve problems such as holes in virtual viewpoint images, achieve obvious three-dimensional effects, high computing efficiency, and eliminate holes

CN102609974AInactive Publication Date: 2012-07-25四川和鼎昇泰信息技术有限公司
4 Cites 17 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2012-07-25
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a virtual viewpoint image generation process on the basis of depth map segmentation and rendering, which includes: (1) acquiring two-dimensional images and a depth map thereof; (2), segmenting the depth map; (3), recovering the two-dimensional images; and (4), rendering the recovered images. By the generation process on the basis of depth map segmentation and rendering, virtual viewpoint images can be synthesized according to the original two-dimensional images and the corresponding depth map, and holes in the synthesized virtual viewpoint images can be eliminated thoroughly. Meanwhile, the virtual viewpoint image generation process can be implemented on hardware systems such as general PC (personal computers) or work stations and the like, higher computation efficiency can be achieved, and the virtual viewpoint images generated are obvious in stereoscopic effect.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of video image processing, and in particular relates to a method for generating virtual viewpoint images based on depth map segmentation and rendering. Background technique

[0002] The generation of virtual viewpoint images is one of the most critical steps in the process of converting 2D images into 3D images. The virtual viewpoint image can be used for roaming between different viewpoints in the free viewpoint image, thereby improving the interactive image viewing experience; it can also be used for multi-viewpoint image coding, and the generated virtual viewpoint image can perform parallax compensation prediction on the actual viewpoint image to play a role The purpose of improving the efficiency of multi-viewpoint image coding. At present, there are mainly two methods for generating virtual viewpoint images: three-dimensional model-based rendering MBR (3D Model Based Rendering) and image-based renderin...

Examples

Embodiment Construction

[0045] In order to describe the present invention more specifically, the method for generating a virtual viewpoint image of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0046] Such as figure 1 As shown, a method for generating a virtual viewpoint image based on depth map segmentation rendering includes the following steps:

[0047] (1) Obtain a two-dimensional image and its depth map.

[0048] the depth corresponding to the original 2D image Figure 1Generally, it is a grayscale image with the same resolution as the two-dimensional image, and each sampling point is 8-bit quantized. If the resolution of the depth map is different from that of the 2D image, the depth map must first be scaled so that its resolution is the same as that of the 2D image, and each sampling point corresponds to each pixel of the 2D image. ; If the depth value of each sampling point of the depth map is not quantized...