Metraipolis › archive › dc_ce7ee67d14f5

Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair — arXiv:2608.20749

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20749
License (as archived)
CC0-1.0
Archived
2026-10-18T10:52:55.264Z
SHA-256 of the archived text
7fd59651523299a1c34206f3baf3dac1bfabb83fb42408b5f973c2aa008de002
Stable URL of this page
https://metraipolis.com/documento/dc_ce7ee67d14f5

How to cite

Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair — arXiv:2608.20749 — arXiv (en), https://arxiv.org/abs/2608.20749 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce7ee67d14f5 (Metraipolis archive dc_ce7ee67d14f5, sha256 7fd59651523299a1c34206f3baf3dac1bfabb83fb42408b5f973c2aa008de002)
BibTeX
@misc{dcce7ee67d14f5,
  title = {Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair — arXiv:2608.20749},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20749},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce7ee67d14f5; sha256 7fd59651523299a1c34206f3baf3dac1bfabb83fb42408b5f973c2aa008de002},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20749. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Identity-preserving video generation aims to synthesize videos that follow natural-language instructions while maintaining the visual identity of a given subject. Recent commercial video generation models have achieved strong visual quality and motion realism, but they still suffer from identity drift, incomplete instruction following, and missing visual details under complex prompts. Since these models are usually closed-source black boxes, directly improving them through parameter optimization is often infeasible. We therefore propose Agentic Enhancement and Semantic Repair (AESR), a lightweight enhancement framework for identity-preserving video generation. To improve prompt construction before generation and mitigate the above failures, AESR introduces a global agentic prompt enhancement module. This module learns model-specific prompting formats from official documentation, acquires human-centered video generation priors from human-interaction data, and accumulates test-domain identity-preserving generation experience into a reusable playbook through an agentic loop. To further repair errors in videos generated with enhanced prompts, AESR introduces a sample-level visual semantic repair module, which uses a VLM to locate erroneous video segments and design repair instructions, edits selected frames into explicit visual references, and guides a video editing model to fix local semantic or identity-related errors. We also adopt a lightweight Mixture-of-Experts selection strategy to choose reliable outputs from different generation and refinement paths. Under the official evaluation protocol of the ACM MM 2026 Identity-Preserving Video Generation Challenge, our system MIPL\_Video ranked first in Track 1, demonstrating the effectiveness of AESR for practical identity-preserving video generation. The code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20749 — 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 2026-10-18T10:48:13.560Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).