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.
Patent Information
- Application Number
- CN202610619440.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-05-08
- Publication Date
- 2026-06-05
AI Technical Summary
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.
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.
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.
Smart Images

Figure CN122156539A_ABST
Abstract
Citation Information
Patent Citations
Drawing method for full-frequency mutual reflection illumination effects in scene
CN103489215A
Underwater three-dimensional reconstruction method and system and storage medium
CN119516079A
Global nerve drawing method and system for multivariate mixed representation scene
CN120612417A
Complex material-oriented global full-frequency illumination neural rendering method and system
CN120726204A
Three-dimensional scene reconstruction method and system based on mixed background and illumination correction
CN120807803A