Metraipolis › archive › dc_5afbc5a8d08a
GEAR: Generative Editing for Scene-Conditioned Outfit Retrieval for VR Travel — arXiv:2611.02363
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02363
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:54:58.041Z
- SHA-256 of the archived text
10948b6a1b6cda085cc3d143c705dd91739e41b7a30975a300d7f9a93f38baa9- Stable URL of this page
https://metraipolis.com/documento/dc_5afbc5a8d08a
How to cite
GEAR: Generative Editing for Scene-Conditioned Outfit Retrieval for VR Travel — arXiv:2611.02363 — arXiv (en), https://arxiv.org/abs/2611.02363 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5afbc5a8d08a (Metraipolis archive dc_5afbc5a8d08a, sha256 10948b6a1b6cda085cc3d143c705dd91739e41b7a30975a300d7f9a93f38baa9)
BibTeX
@misc{dc5afbc5a8d08a,
title = {GEAR: Generative Editing for Scene-Conditioned Outfit Retrieval for VR Travel — arXiv:2611.02363},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02363},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5afbc5a8d08a; sha256 10948b6a1b6cda085cc3d143c705dd91739e41b7a30975a300d7f9a93f38baa9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02363. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In virtual environments, choosing appropriate outfits requires contextual harmony with surrounding scenes, yet bridging the visual gap between 3D ambient views and catalog garment assets remains challenging. This paper investigates scene-conditioned outfit retrieval for interactive 3D environments, where a user's egocentric view serves as the retrieval signal. We present GEAR (Generative Editing for Asset Retrieval), a framework that bridges the cross-domain gap by synthesizing intermediate visual queries rather than predicting direct compatibility. GEAR uses a vision-language model to describe suitable clothing from a captured scene, employs an instruction-guided diffusion model to render the concept onto a standardized reference character, and utilizes the cropped clothing region to retrieve existing 2D outfit assets via embedding similarity. An interactive Unity prototype demonstrates real-time scene capture, asset retrieval, and in-engine 3D avatar fitting. We benchmark GEAR against direct visual similarity, aesthetic scoring, and VLM-based reranking on a controlled dataset using automated Swiss-system pairwise judgments, where GEAR achieves competitive top-ranked performance (mean Elo@5 of 1012.75 and top-10 overlap of 0.180) alongside 0.539 pairwise agreement. Furthermore, a user study across 20 virtual travel scenes demonstrates that GEAR achieves the highest overall participant preference in both visual appeal (34.5%) and contextual suitability (34.5%). 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/2611.02363 — 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 2026-11-03T18:16:52.992Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).