Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911496520335360 |
|---|---|
| author | Gao, Yuanyuan Li, Hao Liu, Yifei Ji, Xinhao Gong, Yuning Liao, Yuanjun Liu, Fangfu Zhang, Manyuan Yang, Yuchen Xu, Dan Yang, Xue Huang, Huaxi Zhang, Hongjie Liu, Ziwei Sun, Xiao Zhang, Dingwen Zhong, Zhihang |
| author_facet | Gao, Yuanyuan Li, Hao Liu, Yifei Ji, Xinhao Gong, Yuning Liao, Yuanjun Liu, Fangfu Zhang, Manyuan Yang, Yuchen Xu, Dan Yang, Xue Huang, Huaxi Zhang, Hongjie Liu, Ziwei Sun, Xiao Zhang, Dingwen Zhong, Zhihang |
| contents | The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets.
In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs.
Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks.
Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07660 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence Gao, Yuanyuan Li, Hao Liu, Yifei Ji, Xinhao Gong, Yuning Liao, Yuanjun Liu, Fangfu Zhang, Manyuan Yang, Yuchen Xu, Dan Yang, Xue Huang, Huaxi Zhang, Hongjie Liu, Ziwei Sun, Xiao Zhang, Dingwen Zhong, Zhihang Computer Vision and Pattern Recognition The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets. In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs. Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks. Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance. |
| title | Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07660 |