Metraipolis › archive › dc_311bbcf5cf00
RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory — arXiv:2609.23286
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23286
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:59:31.205Z
- SHA-256 of the archived text
2f23b513ec02f099f7de0868ddb41bf0fe962db1c6cfbec94df520b5f0f2a0a4- Stable URL of this page
https://metraipolis.com/documento/dc_311bbcf5cf00
How to cite
RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory — arXiv:2609.23286 — arXiv (en), https://arxiv.org/abs/2609.23286 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_311bbcf5cf00 (Metraipolis archive dc_311bbcf5cf00, sha256 2f23b513ec02f099f7de0868ddb41bf0fe962db1c6cfbec94df520b5f0f2a0a4)
BibTeX
@misc{dc311bbcf5cf00,
title = {RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory — arXiv:2609.23286},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23286},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_311bbcf5cf00; sha256 2f23b513ec02f099f7de0868ddb41bf0fe962db1c6cfbec94df520b5f0f2a0a4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23286. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference context cannot be retained under limited GPU this http URL studies seek to resolve this problem via a trade-off between the integrity of inference context and GPU memory usage, which either suffer from a rapid memory inflation or degraded context integrity due to artificially capping memory this http URL by our key observation that the initial saliency of a token reliably dictates its long-term importance across the stream, we propose RegVGGT, a training-free token regulation method which aggressively regulates the tokens of incoming this http URL admitting at most 1% of tokens per frame to update the context memory, our method dramatically suppresses memory inflation as the stream this http URL with a FlashAttention-compatible token saliency estimation scheme, RegVGGT is capable of processing thousands of frames on a consumer-grade GPU with negligible compromise to reconstruction this http URL experiments demonstrate that RegVGGT achieves state-of-the-art performance on long-horizon benchmarks across diverse FFRM prediction tasks, surpassing prior FFRM-based stream reconstruction baselines by a large margin. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.23286 — 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 2026-10-09T21:45:20.872Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).