Advancing Immersive Content Delivery with Dynamic 3D Gaussian Splatting
Workshop on Mobile Computing Systems and Applications（2025）
George Mason University
Abstract
Delivering interactive immersive content is essential for emerging augmented, virtual, and mixed reality (AR/VR/MR) applications. However, conventional 3D content representations, such as point clouds and meshes, struggle to capture highly realistic details. While neural radiance fields (NeRF) can generate high-quality content, it encounters issues with real-time rendering on mobile devices. The recent advent of 3D Gaussian splatting (3DGS) offers a promising alternative that enables photo-realistic rendering with lower computational demands than NeRF. Nevertheless, streaming 3DGS-based immersive content to mobile headsets faces significant challenges, including slow computation on mobile devices, long training time for live streaming, and high bandwidth consumption. To tackle these issues, we present a comprehensive research agenda to advance immersive content delivery by leveraging dynamic 3DGS and exploring practical solutions for both video-on-demand and live video streaming services. Our preliminary results demonstrate the potential of our proposed schemes, laying the groundwork for future research.
MoreTranslated text
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined