Metraipolis › archive › dc_25f14facfa11

Beyond Global Realism: Virtual Try-On Evaluation and Optimization with Dimension-wise Garment Fidelity Assessment — arXiv:2608.29804

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29804
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:08.012Z
SHA-256 of the archived text
6436f4a666060b492ede6036c2fb464d3f98b2ef67dae41cb87b1fb93997fbef
Stable URL of this page
https://metraipolis.com/documento/dc_25f14facfa11

How to cite

Beyond Global Realism: Virtual Try-On Evaluation and Optimization with Dimension-wise Garment Fidelity Assessment — arXiv:2608.29804 — arXiv (en), https://arxiv.org/abs/2608.29804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25f14facfa11 (Metraipolis archive dc_25f14facfa11, sha256 6436f4a666060b492ede6036c2fb464d3f98b2ef67dae41cb87b1fb93997fbef)
BibTeX
@misc{dc25f14facfa11,
  title = {Beyond Global Realism: Virtual Try-On Evaluation and Optimization with Dimension-wise Garment Fidelity Assessment — arXiv:2608.29804},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29804},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25f14facfa11; sha256 6436f4a666060b492ede6036c2fb464d3f98b2ef67dae41cb87b1fb93997fbef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Virtual try-on (VTON) requires not only realistic generation but also faithful preservation of garment characteristics. However, existing evaluation metrics such as PSNR, SSIM, KID and FID struggle to measure the consistency between the generated and reference garments, particularly in capturing the multi-dimensional characteristics of garment fidelity. To address this, we propose DAT: a Dimension-wise Assessment framework for virtual Try-on, which decomposes garment consistency into seven interpretable dimensions: silhouette, color, neckline and sleeve shape, major decoration and structure, material texture, fine-detail fidelity, and logo preservation, each formulated as a discrete attribute-level prediction task. To train this specialized assessment model, we adopt a two-stage learning paradigm comprising large-scale weak supervision on 50K samples, followed by refinement on 10K higher-quality annotations obtained via multi-model voting. Furthermore, we employ weighted cross-entropy loss to mitigate the severe label imbalance inherent across evaluation dimensions. Beyond its role as an evaluation framework, the assessment model can be integrated into reinforcement learning optimization of Qwen-Image-Edit for VTON, where dimension-wise rewards are adaptively aggregated to emphasize under-optimized aspects during training. Experimental results show that our method (8B parameters) achieves state-of-the-art performance in terms of balanced accuracy, SROCC, and PLCC, outperforming strong proprietary models such as Gemini-3.1, Qwen3.7-plus, and GPT-5.5, while also serving as an effective optimization signal for reward-guided VTON 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/2608.29804 — 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 2026-10-17T09:28:48.069Z 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).