Detail publikačního výsledku

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

CHLUBNA, T.; ZEMČÍK, P.; MILET, T.

Originální název

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

Anglický název

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

Druh

Článek WoS

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

CHLUBNA, T.; ZEMČÍK, P.; MILET, T.

Rok RIV

2025

Vydáno

10.06.2024

ISSN

1047-3203

Periodikum

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION

Svazek

2024

Číslo

102

Stát

Spojené státy americké

Strany od

1

Strany do

14

Strany počet

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"
}