Work

Realization and Experimental Research on Immersive Visual Communication System Based on Real-Time Rendering

Year: 2025

Type: conference-paper

Abstract: Aiming at the problems of low image processing efficiency and insufficient rendering quality in virtual reality content creation, a real-time rendering system based on deep learning is designed and realized. An improved U-Net network structure is used for image processing, and a rendering speed of 112fps is realized in a standard test environment, with the end-to-end delay controlled within 12ms. The system achieves a task completion rate of 95.8% and a satisfaction score of 4.6 in a test with 1000 users. The experimental results show that the system significantly improves the rendering efficiency and interactive experience, and provides reliable technical support for virtual reality content creation.

Source: International Conference on Generative Artificial Intelligence and Information Security (GAIIS)

DOI: 10.1145/3728725.3728814

Authors: Shani Liu, Shan Wang, He Zhao

Institutions: Xi'an Eurasia University, Xi'an Academy of Fine Arts

Language: English

Topic: Computer Graphics and Visualization Techniques

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4411016434

FWCI: 2.583

Cites: 3

Cited by: 2

Related to: 10