Metraipolis › archive › dc_d62029bc8fcc

GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing — arXiv:2609.00525

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00525
License (as archived): CC0-1.0
Archived: 2026-10-17T07:10:40.430Z
SHA-256 of the archived text: 6706c59735af40fd46f468b5dc9f6f0ebbc7df0ddb1ce5602e52f2143c43996b
Stable URL of this page: https://metraipolis.com/documento/dc_d62029bc8fcc

How to cite

GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing — arXiv:2609.00525 — arXiv (en), https://arxiv.org/abs/2609.00525 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d62029bc8fcc (Metraipolis archive dc_d62029bc8fcc, sha256 6706c59735af40fd46f468b5dc9f6f0ebbc7df0ddb1ce5602e52f2143c43996b)

BibTeX

@misc{dcd62029bc8fcc,
  title = {GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing — arXiv:2609.00525},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00525},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d62029bc8fcc; sha256 6706c59735af40fd46f468b5dc9f6f0ebbc7df0ddb1ce5602e52f2143c43996b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00525. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render familiar objects at implausible relative sizes. To measure this failure mode, we introduce GenScale, a benchmark and evaluation protocol for real-world relative object scale in image generation and editing. GenScale contains 900 image-level entries and 1,643 pairwise anchor-target scale relations across common-object generation, human-product generation with metric dimensions, and scale correction from failed generations. We further design a human-calibrated ordinal judge for scalable pairwise scale evaluation. Last but not the least, we introduce Rescale, a model-agnostic post-processing agent for localized scale correction without modifying the source generator. Experiments reveal that state-of-the-art image generators and editors cannot reliably observe relative scale yet, while Rescale consistently improves scale plausibility across generated and edited images. Together, GenScale establishes relative object scale as a distinct, measurable, and actionable capability for image generation systems.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00525 — 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 2026-10-17T07:00:58.908Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).