|
--- |
|
license: apache-2.0 |
|
--- |
|
# DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model |
|
[Gwanghyun Kim](https://gwang-kim.github.io/), [Se Young Chun](https://icl.snu.ac.kr/pi) <br> |
|
CVPR 2023 <br> |
|
[gwang-kim.github.io/datid_3d](gwang-kim.github.io/datid_3d/) |
|
|
|
|
|
We propose DATID-3D, a novel pipeline of text-guided domain adaptation tailored for 3D generative models using text-to-image diffusion models that can synthesize diverse images per text prompt without collecting additional images and camera information for the target domain.** Unlike 3D extensions of prior text-guided domain adaptation methods, our novel pipeline was able to fine-tune the state-of-the-art 3D generator of the source domain to synthesize high resolution, multi-view consistent images in text-guided targeted domains without additional data, outperforming the existing text-guided domain adaptation methods in diversity and text-image correspondence. Furthermore, we propose and demonstrate diverse 3D image manipulations such as one-shot instance-selected adaptation and single-view manipulated 3D reconstruction to fully enjoy diversity in text. |
|
|
|
## Fine-tuned 3D generative models |
|
|
|
Fine-tuned 3D generative models using DATID-3D pipeline are stored as `*.pkl` files. |
|
You can download the models in [our Hugginface model pages](https://huggingface.co/gwang-kim/datid3d-finetuned-eg3d-models/tree/main/finetuned_models). |
|
|
|
|
|
## Citation |
|
|
|
``` |
|
@inproceedings{kim2022datid3d, |
|
author = {DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model}, |
|
title = {Gwanghyun Kim and Se Young Chun}, |
|
booktitle = {CVPR}, |
|
year = {2023} |
|
} |
|
``` |
|
|
|
======================================================== |
|
|
