A global neural rendering method and system for end-to-end hybrid representation of full frequency domain lighting

By combining a hybrid representation of meshes and 3D Gaussian splashing with a dual-path neural lighting network, along with Gaussian object region masking, the problem of insufficient rendering performance and image quality of full-frequency domain lighting is solved, achieving efficient full-frequency domain lighting effects.

CN122156539APending Publication Date: 2026-06-05ZHEJIANG UNIV
View PDF 8 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ZHEJIANG UNIV
Filing Date
2026-05-08
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve end-to-end full-frequency domain lighting effects, especially in dynamic scenes and complex optical path processing. Furthermore, existing methods cannot efficiently integrate neural scene representation and global illumination modules simultaneously, resulting in insufficient rendering performance and image quality.

Method used

A hybrid scene representation combining mesh and 3D Gaussian splashing is adopted. Low-frequency and high-frequency illumination are processed separately through a dual-path neural lighting network. Gaussian object region occlusion is introduced for training constraints and inference hybridization to achieve full-frequency domain illumination coverage.

Benefits of technology

While maintaining high-quality global illumination, it significantly improves rendering performance, supports dynamic scenes and complex lighting interactions, and enhances the representation of complex geometry and temporal consistency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122156539A_ABST
    Figure CN122156539A_ABST
Patent Text Reader

Abstract

The application discloses a kind of end-to-end hybrid representation global neural rendering method and system of full frequency domain illumination, belong to computer graphics technical field, including: using the hybrid representation of grid and three-dimensional Gaussian splashing is carried out scene modeling, generates grid geometry buffer, Gaussian buffer and Gaussian object area mask;General global illumination sub-network is based on grid geometry buffer and Gaussian buffer prediction non-Gaussian object area general scene color;Special effect global illumination sub-network is based on Gaussian buffer prediction Gaussian object color and the residual color of Gaussian object to background influence;According to Gaussian object area mask, layer mixing is carried out to general scene color, Gaussian object color and residual color, and final pixel color is obtained, and output rendering image is carried out.The application can realize the cooperation of grid and three-dimensional Gaussian hybrid scene representation and the full frequency domain coverage of double-path neural illumination facing light source and object, significantly improve rendering performance under the premise of guaranteeing high-quality global illumination quality.
Need to check novelty before this filing date? Find Prior Art