Metraipolis › archive › dc_42fbdcff14db

CoANeRV: Coordinate-Aware Token-Space Neural Video Representation — arXiv:2608.13938

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13938
License (as archived)
CC0-1.0
Archived
2026-10-19T04:04:18.099Z
SHA-256 of the archived text
092c9ab7251a6be7c9ca0e795ca94f59702d34815c0e1501d115699876ea8421
Stable URL of this page
https://metraipolis.com/documento/dc_42fbdcff14db

How to cite

CoANeRV: Coordinate-Aware Token-Space Neural Video Representation — arXiv:2608.13938 — arXiv (en), https://arxiv.org/abs/2608.13938 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_42fbdcff14db (Metraipolis archive dc_42fbdcff14db, sha256 092c9ab7251a6be7c9ca0e795ca94f59702d34815c0e1501d115699876ea8421)
BibTeX
@misc{dc42fbdcff14db,
  title = {CoANeRV: Coordinate-Aware Token-Space Neural Video Representation — arXiv:2608.13938},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13938},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_42fbdcff14db; sha256 092c9ab7251a6be7c9ca0e795ca94f59702d34815c0e1501d115699876ea8421},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13938. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural representations for videos (NeRV) have shown strong reconstruction fidelity by storing video-specific information in network weights. However, existing formulations typically require either costly per-video optimization or video-specific weight generation, making it difficult to scale to efficient amortized video representation. We propose CoANeRV, a coordinate-aware token-space framework that adapts the broader token-conditioned neural-field paradigm to amortized video representation. CoANeRV forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder to reconstruct continuous spatio-temporal queries, avoiding per-video decoder optimization or generation while retaining coordinate-level reconstruction flexibility. To make token-space reconstruction effective, CoANeRV introduces a coordinate-aware decoding architecture that aligns spatio-temporal queries with video tokens through axis-adaptive positional encoding and temperature-modulated cross-attention. Block-wise coordinate querying further reduces peak attention memory, making high-resolution reconstruction practical. Experiments on diverse video datasets show that CoANeRV consistently improves reconstruction quality over prior feed-forward NeRV and INR baselines, reduces peak memory compared with attention-based coordinate decoders, and provides efficient amortized encoding without per-video optimization. These results support the proposed video-specific combination of feed-forward token formation, spatio-temporal coordinate retrieval, and memory-bounded dense querying. The code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.13938 — 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 2026-10-19T03:57:57.844Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).