Lates News

Reporters learned that the open-source dataset InteriorGS recently released by the group core technology has topped the global AI open-source community HuggingFace trend list. Following closely behind is the Nemotron-Post dataset launched by Nvidia. Also on the list is another 3D dataset, InteriorAgent, released by the group core. It is understood that the 3D Gaussian semantic dataset InteriorGS which topped the list for the first time, has introduced 3D Gaussian technology into the field of AI space training for the first time, and combined with its self-developed spatial large model capabilities, making the dataset realistic and semantic, becoming the world's first large-scale 3D dataset suitable for intelligent agents' free movement. The InteriorGS dataset consists of 1000 Gaussian scenes covering more than 80 environmental types and over 554,000 item labels belonging to 755 categories. Each object is equipped with a 3D bounding box and semantic annotation.