According to Shangtang Technology, on July 13, Shangtang officially released and fully open source the Nissin SenseNova-Vision understanding and generation of a unified visual model. This is an important visual capability upgrade for the Shangtang Rishin Big Model System. The core transformation of SenseNova-Vision is to make vision a native ability of the general basic model and fully integrate it into the big model system. All classic vision tasks, such as target detection, image segmentation, depth prediction, 3D reconstruction, etc., have been natively unified.

According to Shangtang Technology, on July 13, Shangtang officially released and fully open source the Nissin SenseNova-Vision understanding and generation of a unified visual model. This is an important visual capability upgrade for the Shangtang Rishin Big Model System. The core transformation of SenseNova-Vision is to make vision a native ability of the general basic model and fully integrate it into the big model system. All classic vision tasks, such as target detection, image segmentation, depth prediction, 3D reconstruction, etc., have been natively unified.