Metraipolis › archive › dc_2da14b46ff09
LocateAnyMesh: Grounding 3D Mesh Queries in 2D Images with Vision-Language Models — arXiv:2611.11692
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11692
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:43:35.072Z
- SHA-256 of the archived text
7677e2e20dbf78a37c0c888b9bb45c5120e5109d3a13f2afe241b2c374267ca2- Stable URL of this page
https://metraipolis.com/documento/dc_2da14b46ff09
How to cite
LocateAnyMesh: Grounding 3D Mesh Queries in 2D Images with Vision-Language Models — arXiv:2611.11692 — arXiv (en), https://arxiv.org/abs/2611.11692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2da14b46ff09 (Metraipolis archive dc_2da14b46ff09, sha256 7677e2e20dbf78a37c0c888b9bb45c5120e5109d3a13f2afe241b2c374267ca2)
BibTeX
@misc{dc2da14b46ff09,
title = {LocateAnyMesh: Grounding 3D Mesh Queries in 2D Images with Vision-Language Models — arXiv:2611.11692},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11692},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2da14b46ff09; sha256 7677e2e20dbf78a37c0c888b9bb45c5120e5109d3a13f2afe241b2c374267ca2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Textured 3D meshes specify object geometry and appearance, making them a natural query for finding a particular asset in an image. We introduce LocateAnyMesh, a vision-language model that uses the mesh itself as part of its prompt. A frozen 3D encoder maps colored surface points to a compact token sequence, which a learned connector places alongside image and instruction tokens. We evaluate two grounding models with PPAT mesh tokens: LAM-Select selects image-region proposals, while LAM-Direct predicts coordinates directly. Neither requires rendered query views or view-template matching. New objects require a single encoder pass and no object-specific fine-tuning. LAM-Select improves localization on the reported real-image suites and the official BOP YCB-V evaluation. Secondary experiments compare mesh encoders, and a LAM-Direct study isolates surface color. A single-seed LAM-Select continuation supplies pointing and mesh-only description evidence without replacing the reported localization model. The results support mesh tokens as a query representation, with remaining limitations in presence decisions, identity binding, proposal coverage, and descriptive fidelity. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.11692 — 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 2026-11-10T18:37:37.652Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).