A Cross-Framework Study of Temporal Information Buffering Strategies for Learned Video Compression

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ho, Kuan-Wei, Chen, Yi-Hsin, Benjak, Martin, Ostermann, Jörn, Peng, Wen-Hsiao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909852620554240
author Ho, Kuan-Wei
Chen, Yi-Hsin
Benjak, Martin
Ostermann, Jörn
Peng, Wen-Hsiao
author_facet Ho, Kuan-Wei
Chen, Yi-Hsin
Benjak, Martin
Ostermann, Jörn
Peng, Wen-Hsiao
contents Recent advances in learned video codecs have demonstrated remarkable compression efficiency. Two fundamental design aspects are critical: the choice of inter-frame coding framework and the temporal information propagation strategy. Inter-frame coding frameworks include residual coding, conditional coding, conditional residual coding, and masked conditional residual coding, each with distinct mechanisms for utilizing temporal predictions. Temporal propagation methods can be categorized as explicit, implicit, or hybrid buffering, differing in how past decoded information is stored and used. However, a comprehensive study covering all possible combinations is still lacking. This work systematically evaluates the impact of explicit, implicit, and hybrid buffering on coding performance across four inter-frame coding frameworks under a unified experimental setup, providing a thorough understanding of their effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15426
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Cross-Framework Study of Temporal Information Buffering Strategies for Learned Video Compression
Ho, Kuan-Wei
Chen, Yi-Hsin
Benjak, Martin
Ostermann, Jörn
Peng, Wen-Hsiao
Image and Video Processing
Recent advances in learned video codecs have demonstrated remarkable compression efficiency. Two fundamental design aspects are critical: the choice of inter-frame coding framework and the temporal information propagation strategy. Inter-frame coding frameworks include residual coding, conditional coding, conditional residual coding, and masked conditional residual coding, each with distinct mechanisms for utilizing temporal predictions. Temporal propagation methods can be categorized as explicit, implicit, or hybrid buffering, differing in how past decoded information is stored and used. However, a comprehensive study covering all possible combinations is still lacking. This work systematically evaluates the impact of explicit, implicit, and hybrid buffering on coding performance across four inter-frame coding frameworks under a unified experimental setup, providing a thorough understanding of their effectiveness.
title A Cross-Framework Study of Temporal Information Buffering Strategies for Learned Video Compression
topic Image and Video Processing
url https://arxiv.org/abs/2510.15426