arXiv - CSCL: "ViewRefer: Grasp the Multi-view Knowledge for 3D …" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance. (arXiv:2303.16894v4 [cs.CV] UPDATED)

http://arxiv.org/abs/2303.16894 #arXiv #NLProc

Dec 06, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation