SenseNova-Vision, an open-source project developed by Shangtang Technology.

According to a message from SenseTime Technology, on July 13th, SenseTime officially released and fully open-sourced the SenseNova-Vision unified visual large model for understanding generation, which is an important upgrade to SenseTime's large model system's visual capabilities. The core change of SenseNova-Vision is: making vision a native capability of general basic models, fully integrating into the large model system. All classic visual tasks such as object detection, image segmentation, depth prediction, 3D reconstruction, etc., have thus achieved native unity.