Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Zhenghao, Zhou, Luping, Hu, Zhihao, Xu, Dong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.04274
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912013984202752
author Chen, Zhenghao
Zhou, Luping
Hu, Zhihao
Xu, Dong
author_facet Chen, Zhenghao
Zhou, Luping
Hu, Zhihao
Xu, Dong
contents Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Although these methods have been very practical in neural image compression (NIC), their application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time; 2), NVC frameworks are generally more complex, with many large components that are not easy to update quickly during encoding. To address the previously mentioned challenges, we have developed a content-adaptive NVC technique called Group-aware Parameter-Efficient Updating (GPU). Initially, to minimize error accumulation, we adopt a group-aware approach for updating encoder parameters. This involves adopting a patch-based Group of Pictures (GoP) training strategy to segment a video into patch-based GoPs, which will be updated to facilitate a globally optimized domain-transferable solution. Subsequently, we introduce a parameter-efficient delta-tuning strategy, which is achieved by integrating several light-weight adapters into each coding component of the encoding process by both serial and parallel configuration. Such architecture-agnostic modules stimulate the components with large parameters, thereby reducing both the update cost and the encoding time. We incorporate our GPU into the latest NVC framework and conduct comprehensive experiments, whose results showcase outstanding video compression efficiency across four video benchmarks and adaptability of one medical image benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04274
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression
Chen, Zhenghao
Zhou, Luping
Hu, Zhihao
Xu, Dong
Image and Video Processing
Computer Vision and Pattern Recognition
Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Although these methods have been very practical in neural image compression (NIC), their application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time; 2), NVC frameworks are generally more complex, with many large components that are not easy to update quickly during encoding. To address the previously mentioned challenges, we have developed a content-adaptive NVC technique called Group-aware Parameter-Efficient Updating (GPU). Initially, to minimize error accumulation, we adopt a group-aware approach for updating encoder parameters. This involves adopting a patch-based Group of Pictures (GoP) training strategy to segment a video into patch-based GoPs, which will be updated to facilitate a globally optimized domain-transferable solution. Subsequently, we introduce a parameter-efficient delta-tuning strategy, which is achieved by integrating several light-weight adapters into each coding component of the encoding process by both serial and parallel configuration. Such architecture-agnostic modules stimulate the components with large parameters, thereby reducing both the update cost and the encoding time. We incorporate our GPU into the latest NVC framework and conduct comprehensive experiments, whose results showcase outstanding video compression efficiency across four video benchmarks and adaptability of one medical image benchmark.
title Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.04274