Metraipolis › archive › dc_b67dbbead410

SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera — arXiv:2609.33462

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33462
License (as archived)
CC0-1.0
Archived
2026-10-07T23:51:38.110Z
SHA-256 of the archived text
fe88801778469e153c1c48faa54d7170b8b48d256ba61066bc21bd1de3d6f91b
Stable URL of this page
https://metraipolis.com/documento/dc_b67dbbead410

How to cite

SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera — arXiv:2609.33462 — arXiv (en), https://arxiv.org/abs/2609.33462 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b67dbbead410 (Metraipolis archive dc_b67dbbead410, sha256 fe88801778469e153c1c48faa54d7170b8b48d256ba61066bc21bd1de3d6f91b)
BibTeX
@misc{dcb67dbbead410,
  title = {SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera — arXiv:2609.33462},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33462},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b67dbbead410; sha256 fe88801778469e153c1c48faa54d7170b8b48d256ba61066bc21bd1de3d6f91b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33462. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use of Multi-modal Large Language Models (MLLMs) for omnidirectional spatial reasoning. However, most MLLMs are trained on conventional 2D perspective images and struggle with the severe distortions and wrap-around discontinuities induced by spherical geometry. Enabling them to generalize to non-Euclidean 3D spaces without retraining therefore remains challenging. We propose SphMind, a training-free, plug-and-play framework that decouples semantic perception from geometric reasoning. Rather than requiring MLLMs to learn spherical geometry internally, SphMind preserves their semantic capabilities while handling geometry externally. We introduce a Spherical Harmonics-based Spatial Graph (SHSG) that models spatial relationships through equivariant transformations on the sphere, together with Inference-Time Geometric Grounding (IGG), a model-agnostic closed-loop optimization process that aligns MLLM representations with spherical geometric constraints during inference. Experiments on three benchmarks show that SphMind achieves over 21.4% average improvement in directional reasoning on MP3D and Stanford2D-3D, outperforms prompt-engineering baselines by 8.7% on the real-world ODI-Bench, and improves rotational invariance by 5.9% under panorama rotations, without additional training or dataset-specific tuning. In-the-wild evaluations further show that SphMind resolves directional reasoning queries that baseline vision-language models fail to answer correctly.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.33462 — 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 2026-10-07T23:29:27.214Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).