Metraipolis › archive › dc_87f49da6625f

DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself — arXiv:2610.20990

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20990
License (as archived)
CC0-1.0
Archived
2026-10-16T10:35:07.165Z
SHA-256 of the archived text
a8acf9a046d4a9e9a622796e37d9d15584ab8eb0236a0b207dad5e3f2988fb0b
Stable URL of this page
https://metraipolis.com/documento/dc_87f49da6625f

How to cite

DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself — arXiv:2610.20990 — arXiv (en), https://arxiv.org/abs/2610.20990 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87f49da6625f (Metraipolis archive dc_87f49da6625f, sha256 a8acf9a046d4a9e9a622796e37d9d15584ab8eb0236a0b207dad5e3f2988fb0b)
BibTeX
@misc{dc87f49da6625f,
  title = {DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself — arXiv:2610.20990},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20990},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87f49da6625f; sha256 a8acf9a046d4a9e9a622796e37d9d15584ab8eb0236a0b207dad5e3f2988fb0b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20990. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatial agents have access to reconstruction and segmentation tools, yet inconsistent predictions and fragmented object identities can prevent their outputs from becoming reliable 3D scene information. A simple oracle experiment exposes this perception bottleneck: replacing tool-predicted perception with ground-truth 3D bounding boxes raises an agent to nearly full score across five object-centric VSI-Bench tasks, while retaining the same reasoning tools. Motivated by this finding, we believe the devil of spatial reasoning lies in 3D itself, and introduce DeSpatial(Devil of Spatial), which explicitly decomposes spatial understanding into perception and reasoning. DeSpatial has a shared 3D perception tool to reconcile independent perception outputs into a unified, metric, gravity-aligned 3D scene. This perception tool has two core components: a) a joint segmentation--depth co-refinement module that consolidates masks of the same object and removes projection artifacts caused by inconsistent segmentation and depth within a single frame; b) a cross-view instance fusion module that consolidate voxel-overlapping instances but not allowed to merge same-frame instances. This fusion module additionally fuses spatially disjoint fragments caused by insufficient multi-view observations, by checking their 3D structure and source mask appearance. After receiving the complete and unified 3D scene information, the agent chooses reasoning or computational tools to solve the spatial problem. DeSpatial achieves leading performance on VSI-Bench, MindCube-Tiny, and ViewSpatial, with additional long-video results on VSI-SUPER, revealing the bottleneck of spatial understanding lies in a precise 3D perception itself.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.20990 — 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 2026-10-16T08:52:02.626Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).