Metraipolis › archive › dc_baa52fb437ec

Video Compression with Graph-inspired Neural Representation — arXiv:2609.05541

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05541
License (as archived)
CC0-1.0
Archived
2026-10-16T15:06:31.547Z
SHA-256 of the archived text
5c0f25a047dd9fd256fb69ef8ef09b167e5b9768074e5ceb15d65523e1bb8183
Stable URL of this page
https://metraipolis.com/documento/dc_baa52fb437ec

How to cite

Video Compression with Graph-inspired Neural Representation — arXiv:2609.05541 — arXiv (en), https://arxiv.org/abs/2609.05541 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_baa52fb437ec (Metraipolis archive dc_baa52fb437ec, sha256 5c0f25a047dd9fd256fb69ef8ef09b167e5b9768074e5ceb15d65523e1bb8183)
BibTeX
@misc{dcbaa52fb437ec,
  title = {Video Compression with Graph-inspired Neural Representation — arXiv:2609.05541},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05541},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_baa52fb437ec; sha256 5c0f25a047dd9fd256fb69ef8ef09b167e5b9768074e5ceb15d65523e1bb8183},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05541. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Implicit Neural Representations (INR) provide a compact and content-adaptive paradigm for video compression, typically representing a video through shared network parameters and frame-indexed embeddings. Compared to conventional or autoencoder-based codecs, these approaches exploit temporal redundancy within videos in an implicit manner, which potentially results in sub-optimal compression performance. In this paper, we propose G-NeRV, a graph-inspired INR that explicitly improves temporal redundancy exploitation in the implicit latent space. Motivated by the total correlation principles in information theory, we construct a temporal neighborhood over frame embeddings and perform message passing to aggregate reusable information from neighboring frames through an adaptive gate controlling the injection of neighboring information. Inspired by the reference frame buffer in conventional video coding, a memory bank mechanism has been further designed to enable efficient temporal-neighbor retrieval under random frame-index sampling in INR training. This new representation model has been integrated into an advanced representation compression framework and compared with existing conventional and neural video codecs. The results show that the G-NeRV codec outperforms the state-of-the-art INR-based codec, NVRC, and the latest standard video codec, VVC VTM, by 8.86\% and 14.68\% (in BD-rate), respectively, measured by PSNR on the UVG dataset.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.05541 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T14:49:56.978Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).