SpatialMosaic: A Multiview VLM Dataset for Partial Visibility

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Kanghee, Lee, Injae, Kwak, Minseok, Hong, Jungi, Ryu, Kwonyoung, Park, Jaesik
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914460477685760
author Lee, Kanghee
Lee, Injae
Kwak, Minseok
Hong, Jungi
Ryu, Kwonyoung
Park, Jaesik
author_facet Lee, Kanghee
Lee, Injae
Kwak, Minseok
Hong, Jungi
Ryu, Kwonyoung
Park, Jaesik
contents The rapid progress of Multimodal Large Language Models (MLLMs) has unlocked the potential for enhanced 3D scene understanding and spatial reasoning. A recent line of work explores learning spatial reasoning directly from multi-view images, enabling MLLMs to understand 3D scenes without explicit 3D reconstructions. Nevertheless, key challenges that frequently arise in real-world environments, such as partial visibility, occlusion, and low-overlap conditions that require spatial reasoning from fragmented visual cues, remain under-explored. To address these limitations, we propose a scalable multi-view data generation and annotation pipeline that constructs realistic spatial reasoning QAs, resulting in SpatialMosaic, a comprehensive instruction-tuning dataset featuring 2M QA pairs. We further introduce SpatialMosaic-Bench, a challenging benchmark for evaluating multi-view spatial reasoning under complex and diverse scenarios, consisting of 1M QA pairs across 6 tasks. Our proposed dataset spans both indoor and outdoor scenes, enabling comprehensive evaluation in diverse real-world scenarios. In addition, we introduce a new baseline for multi-view settings, SpatialMosaicVLM, a hybrid framework that integrates 3D reconstruction models as geometry encoders within VLMs for robust spatial reasoning. Extensive experiments demonstrate that our proposed dataset effectively enhances spatial reasoning under challenging multi-view conditions, validating the effectiveness of our data generation pipeline in constructing realistic and challenging QAs. Code and dataset will be available soon.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23365
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpatialMosaic: A Multiview VLM Dataset for Partial Visibility
Lee, Kanghee
Lee, Injae
Kwak, Minseok
Hong, Jungi
Ryu, Kwonyoung
Park, Jaesik
Computer Vision and Pattern Recognition
The rapid progress of Multimodal Large Language Models (MLLMs) has unlocked the potential for enhanced 3D scene understanding and spatial reasoning. A recent line of work explores learning spatial reasoning directly from multi-view images, enabling MLLMs to understand 3D scenes without explicit 3D reconstructions. Nevertheless, key challenges that frequently arise in real-world environments, such as partial visibility, occlusion, and low-overlap conditions that require spatial reasoning from fragmented visual cues, remain under-explored. To address these limitations, we propose a scalable multi-view data generation and annotation pipeline that constructs realistic spatial reasoning QAs, resulting in SpatialMosaic, a comprehensive instruction-tuning dataset featuring 2M QA pairs. We further introduce SpatialMosaic-Bench, a challenging benchmark for evaluating multi-view spatial reasoning under complex and diverse scenarios, consisting of 1M QA pairs across 6 tasks. Our proposed dataset spans both indoor and outdoor scenes, enabling comprehensive evaluation in diverse real-world scenarios. In addition, we introduce a new baseline for multi-view settings, SpatialMosaicVLM, a hybrid framework that integrates 3D reconstruction models as geometry encoders within VLMs for robust spatial reasoning. Extensive experiments demonstrate that our proposed dataset effectively enhances spatial reasoning under challenging multi-view conditions, validating the effectiveness of our data generation pipeline in constructing realistic and challenging QAs. Code and dataset will be available soon.
title SpatialMosaic: A Multiview VLM Dataset for Partial Visibility
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.23365