Metraipolis › archive › dc_49fa76fea881
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing — arXiv:2608.05485
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05485
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:35:57.178Z
- SHA-256 of the archived text
f6e1a964c753edb2801ea23b6f3e60decf78260070c0767b087515abeb3c9f7c- Stable URL of this page
https://metraipolis.com/documento/dc_49fa76fea881
How to cite
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing — arXiv:2608.05485 — arXiv (en), https://arxiv.org/abs/2608.05485 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49fa76fea881 (Metraipolis archive dc_49fa76fea881, sha256 f6e1a964c753edb2801ea23b6f3e60decf78260070c0767b087515abeb3c9f7c)
BibTeX
@misc{dc49fa76fea881,
title = {VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing — arXiv:2608.05485},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05485},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49fa76fea881; sha256 f6e1a964c753edb2801ea23b6f3e60decf78260070c0767b087515abeb3c9f7c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05485. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Evaluating generated videos remains challenging because existing benchmarks rely on fixed evaluation content, cover only a subset of generation and editing settings, and provide limited evidence for their scores. We introduce VideoArgus, a unified rubric-grounded framework covering five video generation and editing settings. For each input instance, VideoArgus generates an output-blind, sample-specific rubric once and reuses it to evaluate all corresponding candidate videos. The rubric defines concrete criteria, scoring rules, failure modes, and evidence plans, which guide criterion-specific VLM QA and visual tools to produce evidence-grounded criterion scores, rationales, and a diagnostic report. We further construct VideoArgus-Bench, containing 1,026 curated input instances built from 653 high-quality images and 416 high-quality videos, with all benchmark rubrics pre-generated, frozen, and released. On a separate 1,260-video human-alignment set, VideoArgus achieves higher within-input Spearman and Kendall correlations with human judgments than the corresponding benchmark-specific evaluators across all five tasks. Model rankings also remain largely consistent across different rubric-generation and evaluation-VLM backbones. All code and data are released. Visit our project page: this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05485 — 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 2026-10-31T10:23:30.975Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).