Metraipolis › archive › dc_0faaf3a474a1

SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning — arXiv:2609.33616

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33616
License (as archived)
CC0-1.0
Archived
2026-10-07T21:01:35.532Z
SHA-256 of the archived text
0ff8763c09f4ac6f30681e61e9394cc5c7f653dba7fe954b6c45305efaaba14b
Stable URL of this page
https://metraipolis.com/documento/dc_0faaf3a474a1

How to cite

SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning — arXiv:2609.33616 — arXiv (en), https://arxiv.org/abs/2609.33616 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0faaf3a474a1 (Metraipolis archive dc_0faaf3a474a1, sha256 0ff8763c09f4ac6f30681e61e9394cc5c7f653dba7fe954b6c45305efaaba14b)
BibTeX
@misc{dc0faaf3a474a1,
  title = {SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning — arXiv:2609.33616},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33616},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0faaf3a474a1; sha256 0ff8763c09f4ac6f30681e61e9394cc5c7f653dba7fe954b6c45305efaaba14b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33616. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) can benefit from geometric priors for multi-view spatial reasoning, yet answer-only training does not directly supervise the intermediate geometric estimates and their use in deriving quantitative spatial answers. We hypothesize that spatial chain-of-thought (CoT) supervision becomes more effective when the VLM first jointly learns complementary local geometry and global scene context through multi-view reconstruction. We introduce SpatialSpeak, a two-stage framework that connects QA-native reconstruction pretraining with spatial CoT learning. In Stage I, QA-Native Reconstruction Pretraining (QA-RP) combines marked-point 3D queries for fine-grained local geometry with object-center queries for global scene context across views. Both tasks are formulated as text-based question answering, allowing geometric estimation and subsequent reasoning to share the same autoregressive output interface. In Stage II, spatial CoT with Visual Compensation (CoT-VC) trains the model to express question-relevant geometric estimates and use them to derive answers, with reliability assessment and visual compensation supporting answer refinement when needed. On ReVSI, QA-RP increases the gain from CoT-VC from 2.6 to 6.9 points, and ablations show that both local and global reconstruction supervision are beneficial. SpatialSpeak achieves state-of-the-art results on ReVSI, VSI-Bench, and SPAR-Bench, with a ReVSI score of 62.8 that exceeds the strongest compared baseline by 8.7 points.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.33616 — 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 2026-10-07T20:29:02.702Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).