Publication Details
Efficient Random-Access GPU Video Decoding for Light-Field Rendering
Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)
Milet Tomáš, Ing., Ph.D. (DCGM)
light field, video decoding, GPU acceleration, image-based rendering
Compression method for GPU streaming of discrete light fields is proposed in this
paper. Views on the scene are encoded with video codec to enable streaming in
real time. Instead of using a classic scheme, all frames are encoded according to
one reference frame. Any frame is decoded directly, in a random-access manner
that is suitable for light-field rendering methods, where only few frames are
necessary on the GPU. The proposed scheme reaches the best decoding quality/time
ratio in comparison to other schemes, where all preceding frames need to be
decompressed, and all-key-frame video that supports random access, but is
extremely large. The proposed method solves the space-requirements and
streaming-bandwidth issues using the GPU accelerated decoding, and enables
incorporating light-field assets in real-time 3D simulations. Compared to
existing methods, the proposal is easy to implement, does not depend on specific
video format or extension and is efficient on consumer GPUs.
@article{BUT189074,
author="Tomáš {Chlubna} and Pavel {Zemčík} and Tomáš {Milet}",
title="Efficient Random-Access GPU Video Decoding for Light-Field Rendering",
journal="JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION",
year="2024",
volume="2024",
number="102",
pages="1--14",
doi="10.1016/j.jvcir.2024.104201",
issn="1047-3203",
url="https://www.sciencedirect.com/science/article/pii/S1047320324001561"
}