Metraipolis › archive › dc_e7060d9bfcf0

SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling — arXiv:2609.34502

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34502
License (as archived)
CC0-1.0
Archived
2026-10-07T23:52:12.200Z
SHA-256 of the archived text
4f45b9bf27982bce5e73763cb554e92357e43379133d27d477e95743dc9a0177
Stable URL of this page
https://metraipolis.com/documento/dc_e7060d9bfcf0

How to cite

SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling — arXiv:2609.34502 — arXiv (en), https://arxiv.org/abs/2609.34502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e7060d9bfcf0 (Metraipolis archive dc_e7060d9bfcf0, sha256 4f45b9bf27982bce5e73763cb554e92357e43379133d27d477e95743dc9a0177)
BibTeX
@misc{dce7060d9bfcf0,
  title = {SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling — arXiv:2609.34502},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34502},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e7060d9bfcf0; sha256 4f45b9bf27982bce5e73763cb554e92357e43379133d27d477e95743dc9a0177},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present SubjectAnchor, a Subject-Aware Memory-to-Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual memories extracted from previous shots. The objective is to preserve subject identity and scene consistency across cuts while retaining the controllability of shot-wise prompting. Built on Wan2.2-I2V-A14B, SubjectAnchor contains three key components: subject-related memory construction, subject-aware temporal rotary position encoding, and memory-aware attention partition. For each target shot, the method constructs a compact memory bank by tracing each required subject to its historical appearance and retrieving the most relevant precomputed keyframes. These memory frames are encoded into the model input as explicit visual conditions, while different subjects are assigned to separated negative temporal slots to reduce identity interference. In addition, memory-aware attention partition regulates the interaction between memory tokens and generated content within a shared backbone. This formulation preserves the appearance anchoring of explicit visual memory while remaining compatible with script-driven shot-by-shot generation. Experiments show that SubjectAnchor improves cross-shot identity consistency over representative memory-based and holistic baselines while maintaining competitive visual quality.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.34502 — 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 2026-10-07T23:29:27.382Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).