Metraipolis › archive › dc_8b93d33deed0
Can 4D Foundation Models Remember? — arXiv:2609.20819
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20819
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:08:07.903Z
- SHA-256 of the archived text
af13c0570cf21332e60f802310528b1f0d75d9a04db6edbdf6ec86865347e1fb- Stable URL of this page
https://metraipolis.com/documento/dc_8b93d33deed0
How to cite
Can 4D Foundation Models Remember? — arXiv:2609.20819 — arXiv (en), https://arxiv.org/abs/2609.20819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b93d33deed0 (Metraipolis archive dc_8b93d33deed0, sha256 af13c0570cf21332e60f802310528b1f0d75d9a04db6edbdf6ec86865347e1fb)
BibTeX
@misc{dc8b93d33deed0,
title = {Can 4D Foundation Models Remember? — arXiv:2609.20819},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20819},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b93d33deed0; sha256 af13c0570cf21332e60f802310528b1f0d75d9a04db6edbdf6ec86865347e1fb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Perceiving and remembering the visual world is fundamental to navigating and interacting with our environment. Current 4D foundation models, such as camera-controllable video models or 4D reconstruction models, can perceive and reconstruct dynamic environments, but how well they remember what they have perceived remains an open question. Existing benchmarks largely rely on pixel-level metrics and lack ground truth for objects once they leave the field of view, making them unable to evaluate visual memory in an object-centric manner against references. To fill this gap, we introduce PersistBench, a dataset and metric suite that leverages 360° videos as omniscient ground truth and proposes three evaluation aspects: object permanence, motion continuity, and appearance preservation. Evaluating various models across diverse categories reveals that current models can only maintain short-term consistency that degrades significantly once objects leave the field of view. Our findings highlight the gap between current model capabilities and robust visual memory ("seeing is not remembering"), providing guidance for future development of 4D foundation models. Dataset and code are available on the project page: this https URL .
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.20819 — 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 2026-10-10T04:26:09.635Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).