Metraipolis › archive › dc_f01cc60e5b2a

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding — arXiv:2609.04741

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04741
License (as archived)
CC0-1.0
Archived
2026-10-16T23:33:28.442Z
SHA-256 of the archived text
f4843c0eaf6ef1be73fe009aaf211aed407cde2a1f6e3c83e70f3edcbc2e712c
Stable URL of this page
https://metraipolis.com/documento/dc_f01cc60e5b2a

How to cite

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding — arXiv:2609.04741 — arXiv (en), https://arxiv.org/abs/2609.04741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f01cc60e5b2a (Metraipolis archive dc_f01cc60e5b2a, sha256 f4843c0eaf6ef1be73fe009aaf211aed407cde2a1f6e3c83e70f3edcbc2e712c)
BibTeX
@misc{dcf01cc60e5b2a,
  title = {Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding — arXiv:2609.04741},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04741},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f01cc60e5b2a; sha256 f4843c0eaf6ef1be73fe009aaf211aed407cde2a1f6e3c83e70f3edcbc2e712c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent zero-shot 3D visual grounding methods leverage vision-language models (VLMs) to localize objects in 3D scenes from natural language queries. However, these methods typically rely on heuristic rules to select which camera views are provided to the VLM, often prioritizing object visibility rather than grounding relevance. We present IVSGround, a framework that learns Influential View Selection for VLM-based 3D visual grounding. Instead of using fixed heuristics, a lightweight view selector is trained to identify views that provide discriminative evidence for grounding. To obtain supervision signals, we generate training signals using feedback from a reasoning VLM through a two-stage rejection sampling process. During inference, the learned selector predicts query-conditioned influential views for each candidate object, which are then evaluated by a frozen reasoning VLM through comparative grounding. Experiments on ScanRefer and NR3D show that IVSGround consistently improves grounding accuracy over existing zero-shot pipelines, demonstrating that selecting where to look is crucial for effective 3D visual grounding. Project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04741 — 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 2026-10-16T23:16:11.401Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).