Global illumination neural rendering method and system based on neural field space-time domain joint supersampling

CN122368293APending Publication Date: 2026-07-10ZHEJIANG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ZHEJIANG UNIV
Filing Date
2026-04-16
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing technologies struggle to balance detail restoration and real-time performance of dynamic objects in global illumination rendering, and lack a unified coordination mechanism between temporal and spatial oversampling and global illumination information, resulting in insufficient illumination representation and excessive computational overhead.

Method used

A spatiotemporal joint supersampling method based on neural fields is adopted. Global illumination information is generated by encoding the dynamic information of the input scene, and spatiotemporal joint supersampling is performed in the independent coordinate space of the object's neural field. The global illumination information and historical features are combined for low-resolution aggregation and fusion to generate high-quality rendering results.

Benefits of technology

It improves the spatial accuracy and temporal stability of global illumination rendering, reduces lighting breaks and edge artifacts, and enhances rendering efficiency and temporal continuity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122368293A_ABST
    Figure CN122368293A_ABST
Patent Text Reader

Abstract

The application discloses a global illumination neural rendering method and system based on neural field space-time domain joint super sampling, which comprises the following steps: encoding input scene dynamic information to generate global illumination information of each object; obtaining current frame position related information and converting to object neural field independent coordinate space to form object position data; performing space-time joint super sampling through a global illumination transformation network combined with historical features; performing low-resolution aggregation and global illumination decoding on the super sampling samples to obtain global illumination features of each object; combining the global illumination features of each object with current frame geometry related information to generate fusion features; encoding and decoding the fusion features in a low-resolution space and performing end upsampling to output rendering results and update historical features. The application realizes global illumination neural rendering by adopting a neural field space-time domain joint super sampling method, and has the advantages of high efficiency, good details and strong time sequence stability.
Need to check novelty before this filing date? Find Prior Art