Metraipolis › archive › dc_db2a867d41ff

Grounding Image Composition with Label-Conditioned Visual Evidence — arXiv:2610.41080

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41080
License (as archived): CC0-1.0
Archived: 2026-11-03T08:20:25.427Z
SHA-256 of the archived text: d90419bebda8274efbb838c0cc7b88ada17343f0208c8f12325f56e4e60be87d
Stable URL of this page: https://metraipolis.com/documento/dc_db2a867d41ff

How to cite

Grounding Image Composition with Label-Conditioned Visual Evidence — arXiv:2610.41080 — arXiv (en), https://arxiv.org/abs/2610.41080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db2a867d41ff (Metraipolis archive dc_db2a867d41ff, sha256 d90419bebda8274efbb838c0cc7b88ada17343f0208c8f12325f56e4e60be87d)

BibTeX

@misc{dcdb2a867d41ff,
  title = {Grounding Image Composition with Label-Conditioned Visual Evidence — arXiv:2610.41080},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db2a867d41ff; sha256 d90419bebda8274efbb838c0cc7b88ada17343f0208c8f12325f56e4e60be87d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image composition labels such as center, diagonal, or rule of thirds describe visual structure rather than object categories. KU-PCP provides image-level labels and class-specific geometric elements, but does not show which visible regions people associate with each of its nine classes. We introduce KU-PCP Elements (KU-PCPE), a label-conditioned region-evidence benchmark for photographic composition. Given an image and a label already judged applicable, the task is to segment the visible regions that explain why the label applies. KU-PCPE contains 4,093 single-annotator training masks and a 1,327-task expert test split with three masks per image-label task. The annotations also include exploratory segment-versus-line ratings that describe whether region or semantic-guideline evidence better explains the label. A held-out expert reaches .867 Dice against the other experts, while the strongest deployable model reaches .664, a proposal oracle .672, and the best vision-language model (VLM) proposal selector .395. KU-PCPE exposes the gap between recognizing a composition label and grounding the human-aligned visual evidence that makes it plausible in a particular image.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41080 — 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 2026-11-03T08:06:38.817Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).