DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model — mentioned by bradkim990

Wed, 05 Apr 2023 11:46:00 GMT

Hi HMs! Happy to share the Code & Gradio demo & Colab demo for our paper, "DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model" (accepted to CVPR2023). We showcase the demo of text-guided manipulated 3D reconstuction (Single-shot Text-guided 2D-to-3D) of the portrait beyond text-guided image manipulation! - Paper: https://arxiv.org/abs/2211.16374 - Project: https://gwang-kim.github.io/datid_3d/ - Code & Colab & Gradio Demo: https://github.com/gwang-kim/DATID-3D DATID-3D succeeded in text-guided domain adaptation of 3D-aware generative models…

Paper and discussion history. A mention is not an endorsement.

DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model · HackerPapers discussions

DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model — mentioned by bradkim990