Metraipolis › archive › dc_c7ef8ffabb2d

NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation — arXiv:2608.30194

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.30194
License (as archived): CC0-1.0
Archived: 2026-10-17T09:59:22.366Z
SHA-256 of the archived text: 395f2fa1e81b44b39929a966e9eb76f29eba6fa89dfeabd0199dc387da517442
Stable URL of this page: https://metraipolis.com/documento/dc_c7ef8ffabb2d

How to cite

NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation — arXiv:2608.30194 — arXiv (en), https://arxiv.org/abs/2608.30194 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7ef8ffabb2d (Metraipolis archive dc_c7ef8ffabb2d, sha256 395f2fa1e81b44b39929a966e9eb76f29eba6fa89dfeabd0199dc387da517442)

BibTeX

@misc{dcc7ef8ffabb2d,
  title = {NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation — arXiv:2608.30194},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30194},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7ef8ffabb2d; sha256 395f2fa1e81b44b39929a966e9eb76f29eba6fa89dfeabd0199dc387da517442},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30194. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attribute binding, spatial relations, and object interactions. While reward-based fine-tuning improves alignment, it is susceptible to reward hacking and adapts poorly to new prompt distributions. In this work, we propose NoisEasier, a test-time scaling framework that improves T2V generation through differentiable reward-guided noise optimization without modifying the underlying model. By combining efficient short-step generators with a multi-objective reward formulation, NoisEasier enables stable and practical test-time optimization under realistic inference budgets. Our key insight is that jointly optimizing the entire stochastic trajectory accelerates reward convergence and improves compositional alignment over optimizing only the initial latent, with negligible additional computational and time cost. Experiments on VBench and T2V-CompBench demonstrate consistent improvements across multiple backbones, achieving over 10% average gains on challenging dimensions such as attribute binding, object interaction, and numeracy. Overall, NoisEasier serves as both a flexible alternative and a complementary enhancement to reward-based fine-tuning, establishing test-time scaling as an effective paradigm for controllable text-to-video generation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.30194 — 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 2026-10-17T09:28:48.119Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).