Indoor Scene Virtual Roaming Method Based on Reflection Decomposition

Abstract

The invention discloses a method for virtual roaming of indoor scenes based on reflection decomposition. Firstly, a rough global triangular mesh model projection is obtained by three-dimensional reconstruction as an initial depth map, and depth edges are aligned to colored edges, and the aligned depth map is converted into simplified triangles. Grid; detect the plane in the global triangular mesh model, if a plane is a reflection plane, construct a two-layer expression on the reflection area for each picture that can see the reflection plane, and use it to render the reflection effect of the object surface correctly; Determine the virtual viewing angle, use the neighborhood image and the triangular grid to draw the virtual viewing angle picture, and use the foreground background picture and the foreground background triangular grid to draw the reflection area. The method of the invention can perform virtual roaming with a large degree of freedom in a relatively large indoor scene containing reflection effects under the condition of relatively small storage requirements. The invention has good rendering effect, large freedom of roaming, can draw partial reflection, high light and other effects, and the result is robust.

Description

technical field [0001] The invention relates to the technical field of image-based rendering and virtual viewpoint synthesis, in particular to a method for virtual roaming of an indoor scene based on an image-based rendering technology combined with reflection decomposition. Background technique [0002] The purpose of virtual roaming in indoor scenes is to build a system that outputs the drawn pictures of the virtual viewpoint given the internal and external parameters of the virtual camera. The existing relatively mature virtual roaming applications are mainly based on a series of panoramic pictures, and a purely rotating virtual roaming can be performed with each panoramic picture as the center. Most systems use simple interpolation to move between panoramic pictures, and the visual error is relatively large at this time . For virtual roaming with large degrees of freedom, there are many existing methods to achieve object-level observation or view point movement observat...

AI Technical Summary

Problems solved by technology

For larger indoor scenes, the latest methods can achieve relatively free viewpoint rendering, but the rendering effect is still not good enough, see Riegler and Koltun. "Free View Synthesis." Proceedings of the European Conference on Computer Vision.2020

In particular, for the various reflection types (ground, table, mirror, etc.) that exist in larger indoor scenes, there is still no system that can handle indoor roaming with such complex materials.

Images