Metraipolis › archive › dc_99a03cb86356

Autonomous Fashion Outfit Composition via Unified Aesthetic Foresight Model — arXiv:2608.13888

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13888
License (as archived)
CC0-1.0
Archived
2026-10-19T02:30:27.561Z
SHA-256 of the archived text
265944f3c5f93d6c3db5cd0aee6d88fdbb54c91886b47ab4abb864d8d249ec6f
Stable URL of this page
https://metraipolis.com/documento/dc_99a03cb86356

How to cite

Autonomous Fashion Outfit Composition via Unified Aesthetic Foresight Model — arXiv:2608.13888 — arXiv (en), https://arxiv.org/abs/2608.13888 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99a03cb86356 (Metraipolis archive dc_99a03cb86356, sha256 265944f3c5f93d6c3db5cd0aee6d88fdbb54c91886b47ab4abb864d8d249ec6f)
BibTeX
@misc{dc99a03cb86356,
  title = {Autonomous Fashion Outfit Composition via Unified Aesthetic Foresight Model — arXiv:2608.13888},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13888},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99a03cb86356; sha256 265944f3c5f93d6c3db5cd0aee6d88fdbb54c91886b47ab4abb864d8d249ec6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13888. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fashion Outfit Composition (FOC) requires sequentially assembling fashion items into a stylistically cohesive ensemble. Existing works struggle to model this step-by-step process effectively, primarily because they fail to jointly optimize the two critical capabilities required for FOC: intermediate outfit value evaluation and complementary item prediction. This structural disconnect, compounded by the severe sparsity of step-wise aesthetic signals, leaves them without a mechanism to autonomously determine when to stop the composition process. To address these challenges, we introduce the Unified Aesthetic Foresight Model (UAFM), which seamlessly unifies both capabilities into a dual-head architecture over a shared backbone. Crucially, we formulate FOC as a deterministic Markov Decision Process and optimize a value head via a post-decision state temporal difference (TD) objective to recursively backpropagate sparse terminal aesthetic rewards to intermediate states. This enables the model to accurately estimate the potential of a partial outfit evolving into a compatible ensemble. Consequently, UAFM can compute step-wise marginal aesthetic gains for dynamic termination. Furthermore, this unified design strictly aligns aesthetic evaluation and complementary item prediction within a shared representation manifold, intrinsically regularizing the combinatorial search space. Extensive experiments on the Polyvore-Outfits dataset demonstrate that UAFM establishes a new state-of-the-art across both FOC and conventional fashion tasks. Extensive ablation studies further confirm that our post-decision state TD formulation provides the aesthetic value prediction necessary for autonomous dynamic termination, while validating the synergistic benefits of our unified dual-head architecture.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13888 — 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 2026-10-19T02:26:17.778Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).