Metraipolis › archive › dc_e70bb929861d
AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning — arXiv:2608.20720
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20720
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:52:55.236Z
- SHA-256 of the archived text
1f5fd5b13f635061cbee9a45de5f084c69a40dd259357ba9fa8ee5ba023d1432- Stable URL of this page
https://metraipolis.com/documento/dc_e70bb929861d
How to cite
AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning — arXiv:2608.20720 — arXiv (en), https://arxiv.org/abs/2608.20720 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e70bb929861d (Metraipolis archive dc_e70bb929861d, sha256 1f5fd5b13f635061cbee9a45de5f084c69a40dd259357ba9fa8ee5ba023d1432)
BibTeX
@misc{dce70bb929861d,
title = {AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning — arXiv:2608.20720},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20720},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e70bb929861d; sha256 1f5fd5b13f635061cbee9a45de5f084c69a40dd259357ba9fa8ee5ba023d1432},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20720. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open-world 3D affordance grounding requires localizing functional object parts in 3D given free-form language queries. Existing methods typically assume pre-built object-centric 3D geometry and closed affordance ontologies, limiting deployment from raw RGB observations. We present AffordAny, an end-to-end framework that uses one monocular RGB image to construct large-scale text-conditioned 3D part supervision, ground affordances with a frozen vision-language model (VLM) guided decoder, and improve open-world generalization through pseudo-label self-training. Our automated pipeline produces a benchmark of 5,334 objects and 10,633 part-level samples spanning 473 categories, an order-of-magnitude increase in categorical diversity over prior work. The decoder progressively fuses frozen Cosmos-2B features with 3D geometry through spatial projection, instruction-conditioned semantic compression, and bidirectional geometry-semantics interaction. Minimal-perturbation pseudo-label self-training further adds new objects without human annotation. Under a systematic generalization protocol evaluating unseen objects, unseen categories, and unseen instruction paraphrases, our approach achieves 0.428 IoU on unseen objects and 0.315 IoU on unseen categories after self-training, with unseen-category mIoU improving by 6.3% relative (p<0.01) and an instruction sensitivity gap of only 0.105, demonstrating effectiveness and robustness of our method. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20720 — 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 2026-10-18T10:48:13.557Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).