.png){kind=icon}
.png){kind=icon}
Return
A GPU-Enabled Framework for Light Field Efficient Compression and Real-Time Rendering
.png){kind=icon}
PRE
AI
DOI：10.1109/TC.2024.3517743.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Real-time rendering offers instantaneous visual feedback, making it crucial for mixed-reality applications. The light field captures both light intensity and direction in a 3D environment, serving as a data-rich medium to enhance mixed-reality experiences. However, two major challenges remain: 1) current light field rendering techniques are unsuitable for real-time computation, and 2) existing real-time methods cannot efficiently process high-dimensional light field data on GPU platforms. To overcome these challenges, we propose an framework utilizing a compact neural representation of light field data, implemented on a GPU platform for real-time rendering. This framework provides both compact storage and high-fidelity real-time computation. Specifically, we introduce a ray global alignment strategy to simplify the framework and improve practicality. This strategy enables the learning of an optimal embedding for all local rays in a globally consistent way, removing the need for camera pose calculations. To achieve effective compression, the neural light field is employed to map each embedded ray to its corresponding color. To enable real-time rendering, we design a novel super-resolution network to enhance rendering speed. Extensive experiments demonstrate that our framework significantly enhances compression efficiency and real-time rendering performance, achieving nearly 50x compression ratio and 100 FPS rendering.
Keywords:
Rendering (computer graphics)
Real-time systems
Light fields
Image coding
Cameras
Neural radiance field
Virtual reality
Graphics processing units
Superresolution
HTTP
Light field compression
light field rendering
GPU-enabled
real-time
neural light field
Journal
IF:
3.8
Papers:
5.3K
Citations:
9.8K