Publication detail

Efficient Random-Access GPU Video Decoding for Light-Field Rendering

CHLUBNA, T. ZEMČÍK, P. MILET, T.

Original Title

Efficient Random-Access GPU Video Decoding for Light-Field Rendering

Type

journal article in Web of Science

Language

English

Original Abstract

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.

Keywords

light field, video decoding, GPU acceleration, image-based rendering

Authors

CHLUBNA, T.; ZEMČÍK, P.; MILET, T.

Released

10. 6. 2024

ISBN

1047-3203

Periodical

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION

Year of study

2024

Number

102

State

United States of America

Pages from

1

Pages to

14

Pages count

14

URL

https://www.sciencedirect.com/science/article/pii/S1047320324001561

BibTex

@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"
}