datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
PhysicalAI-SpatialIntelligence-Lyra-SDG
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Paper, Project Page, Code
Sherwin Bahmani,
Tianchang Shen,
Jiawei Ren,
Jiahui Huang,
Yifeng Jiang,
Haithem Turki,
Andrea Tagliasacchi,
David B. Lindell,
Zan Gojcic,
Sanja Fidler,
Huan Ling,
Jun Gao,
Xuanchi Ren
Dataset Description:
The PhysicalAI-SpatialIntelligence-Lyra-SDG Dataset is a multi-view 3D and 4D dataset generated using GEN3C.
The 3D reconstruction setup uses 59,031 images… See the full description on the dataset page: https://huggingface.co/datasets/nvidia/PhysicalAI-SpatialIntelligence-Lyra-SDG.PhysicalAI-Spatial-Intelligence-Warehouse
Physical AI Spatial Intelligence Warehouse
Overview
The Physical AI Spatial Intelligence Warehouse is a comprehensive synthetic dataset designed to advance 3D scene understanding in warehouse environments. Generated using NVIDIA's Omniverse, this dataset focuses on spatial reasoning through natural language question-answering pairs that cover four key categories: spatial relationships (left/right), multi-choice questions, distance measurements, and object counting. Each… See the full description on the dataset page: https://huggingface.co/datasets/nvidia/PhysicalAI-Spatial-Intelligence-Warehouse.Spatial_Intelligence_Understanding