You Only Render Once: Enhancing Energy and Computation Efficiency of Mobile Virtual Reality

2025-06-18

AI Summary

To address the computational and energy bottlenecks in mobile VR caused by rendering stereo images twice independently, this paper proposes EffVR, an efficient single-rendering stereo synthesis framework. Methodologically, EffVR pioneers pixel-level geometric guidance—leveraging depth and surface normal maps—to synthesize stereo views from a single monocular render, thereby departing from conventional dual-rendering paradigms. It integrates monocular rendering, explicit disparity modeling, a lightweight reprojection network, and co-optimized scheduling for mobile GPU execution. Extensive experiments demonstrate that EffVR achieves, on average, a 27% reduction in power consumption, a 115.2% increase in frame rate, and high perceptual fidelity with SSIM of 0.9679 and PSNR of 34.09, outperforming state-of-the-art methods. The source code and an Android application are publicly released.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Efficient ML / Green AI

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Mobile Virtual Reality (VR) is essential to achieving convenient and immersive human-computer interaction and realizing emerging applications such as Metaverse. However, existing VR technologies require two separate renderings of binocular images, causing a significant bottleneck for mobile devices with limited computing capability and power supply. This paper proposes an approach to rendering optimization for mobile VR called EffVR. By utilizing the per-pixel attribute, EffVR can generate binocular VR images from the monocular image through genuinely one rendering, saving half the computation over conventional approaches. Our evaluation indicates that, compared with the state-of-art, EffVRcan save 27% power consumption on average while achieving high binocular image quality (0.9679 SSIM and 34.09 PSNR) in mobile VR applications. Additionally, EffVR can increase the frame rate by 115.2%. These results corroborate EffVRsuperior computation/energy-saving performance, paving the road to a sustainable mobile VR. The source code, demo video, android app, and more are released anonymously at https://yoro-vr.github.io/

Problem

• Reducing dual rendering bottleneck in mobile VR
• Improving energy efficiency for mobile VR devices
• Enhancing computation speed in VR image generation

Innovation

• Generates binocular images from monocular rendering
• Reduces power consumption by 27% on average
• Increases frame rate by 115.2%