Metraipolis › archive › dc_d3cebbd1fc3b

SE-Mem: Semantic-Episodic Memory for Scene-Consistent Generative View Synthesis — arXiv:2611.00658

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00658
License (as archived)
CC0-1.0
Archived
2026-11-03T11:40:43.781Z
SHA-256 of the archived text
3ee3275308ae1ea432ea5563593aca5ce4f84b018d8acaa57bcf80613210b335
Stable URL of this page
https://metraipolis.com/documento/dc_d3cebbd1fc3b

How to cite

SE-Mem: Semantic-Episodic Memory for Scene-Consistent Generative View Synthesis — arXiv:2611.00658 — arXiv (en), https://arxiv.org/abs/2611.00658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3cebbd1fc3b (Metraipolis archive dc_d3cebbd1fc3b, sha256 3ee3275308ae1ea432ea5563593aca5ce4f84b018d8acaa57bcf80613210b335)
BibTeX
@misc{dcd3cebbd1fc3b,
  title = {SE-Mem: Semantic-Episodic Memory for Scene-Consistent Generative View Synthesis — arXiv:2611.00658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3cebbd1fc3b; sha256 3ee3275308ae1ea432ea5563593aca5ce4f84b018d8acaa57bcf80613210b335},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative view synthesis aims to synthesize novel-view videos from reference observations along user-defined camera trajectories. Maintaining global scene consistency throughout this process remains challenging for camera-conditioned interactive video generators. Existing approaches typically select reference frames based solely on camera poses, overlooking whether the content remains semantically relevant or even visible. To address these limitations, we draw inspiration from semantic and episodic memory in human cognition, in which semantic memory captures generalized knowledge across experiences, whereas episodic memory preserves information tied to specific past events and contexts. Motivated by the complementary roles of semantic and episodic memory, we introduce SE-Mem, a Semantic-Episodic Memory framework that organizes historical observations in a structured 3D representation and augments its elements with semantic importance scores. A two-stage memory retrieval strategy is designed to identify the most informative frames to provide contextual guidance. Taking into account both semantic significance and geometric visibility, SE-Mem preserves semantic coherence and fine-grained visual details during novel view synthesis. Extensive evaluations show that our approach improves visual quality and achieves competitive geometric consistency across multiple benchmarks.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00658 — 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 2026-11-03T11:06:37.438Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).