Metraipolis › archive › dc_d8db23bbd213
MagicGarment: Benchmarking Single-Image Standalone 3D Garment Reconstruction — arXiv:2610.19623
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19623
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:56:18.024Z
- SHA-256 of the archived text
2efc2f15b19d5609b3541e456a7ba7c44630aa7442863dd56f3cebec11a70700- Stable URL of this page
https://metraipolis.com/documento/dc_d8db23bbd213
How to cite
MagicGarment: Benchmarking Single-Image Standalone 3D Garment Reconstruction — arXiv:2610.19623 — arXiv (en), https://arxiv.org/abs/2610.19623 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8db23bbd213 (Metraipolis archive dc_d8db23bbd213, sha256 2efc2f15b19d5609b3541e456a7ba7c44630aa7442863dd56f3cebec11a70700)
BibTeX
@misc{dcd8db23bbd213,
title = {MagicGarment: Benchmarking Single-Image Standalone 3D Garment Reconstruction — arXiv:2610.19623},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19623},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8db23bbd213; sha256 2efc2f15b19d5609b3541e456a7ba7c44630aa7442863dd56f3cebec11a70700},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19623. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Single-image 3D reconstruction has advanced rapidly, yet standalone garments remain challenging due to thin-shell geometry, open boundaries, and layered structures. Existing datasets and evaluation protocols provide limited support for systematic evaluation in this setting. We introduce MagicGarment, a benchmark for single-image standalone 3D garment reconstruction with 1,518 professionally constructed assets across 17 composite garment types, aligned multimodal annotations, and a unified evaluation protocol. We further establish a garment-aware reference baseline by adapting a pretrained image-to-3D backbone at two levels: Grounded Semantic Refinement (GSR) provides garment-focused visual conditioning, while Flow-Time-Route LoRA (FTR-LoRA) adapts the frozen 3D generative backbone using flow-timestep, token-routing, and expert-load information. Experiments demonstrate MagicGarment's benchmark utility and the effectiveness of garment-aware adaptation. Project page: this https URL . 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/2610.19623 — 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 2026-10-15T21:38:29.480Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).