Title:
METHOD AND SYSTEM FOR THREE-DIMENSIONAL VIDEO RECONSTRUCTION BASED ON NERF COMBINATION OF MULTI-VIEW LAYERS
Document Type and Number:
WIPO Patent Application WO/2024/055211
Kind Code:
A1
Abstract:
The present invention provides a method and system for three-dimensional video reconstruction based on combination of NeRF multi-view layers. The method comprises: utilizing a photo covering a full scene to model a first frame in a multi-path synchronous video by means of a static NeRF, and obtaining global static information comprising a foreground and a background; then, according to implicit voxel density information therein, marking a region that has a human; and splicing a dynamic human NeRF model into a selected region; and finally, a free viewpoint 3D video of the static background plus a dynamic character can be obtained by means of unified volume rendering. In combination with depth information outputted by the static NeRF, an ultra-long distance mask and a mid-short distance mask are divided, such that the static NeRF modeling can be directly performed out on a middle-near static scene only on the basis of the middle-near distance mask, so as to reduce the operation amount of the static NeRF model and increase rendering speed.
Inventors:
ZHANG ZEHENG (CN)
ZHANG YAN (CN)
ZHANG YAN (CN)
Application Number:
PCT/CN2022/118818
Publication Date:
March 21, 2024
Filing Date:
September 14, 2022
Export Citation:
Assignee:
BEIJING YUANCHUANGLI TECH CO LTD (CN)
International Classes:
G06T19/00; G06T17/00
Domestic Patent References:
| WO2022164895A2 | 2022-08-04 |
Foreign References:
| CN114863038A | 2022-08-05 | |||
| CN114627223A | 2022-06-14 |
Attorney, Agent or Firm:
LECOME INTELLECTUAL PROPERTY AGENT LTD. (CN)
Download PDF: