Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,11 @@ The LDM3D model was proposed in ["LDM3D: Latent Diffusion Model for 3D"](https:/
|
|
| 16 |
|
| 17 |
LDM3D got accepted to [CVPRW'23]([https://aaai.org/Conferences/AAAI-23/](https://cvpr2023.thecvf.com/)).
|
| 18 |
|
| 19 |
-
This checkpoint finetunes the previous [ldm3d-4c](https://huggingface.co/Intel/ldm3d-4c) on 2 panoramic-images datasets:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
A demo using this checkpoint has been open sourced in [this space](https://huggingface.co/spaces/Intel/ldm3d)
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
LDM3D got accepted to [CVPRW'23]([https://aaai.org/Conferences/AAAI-23/](https://cvpr2023.thecvf.com/)).
|
| 18 |
|
| 19 |
+
This checkpoint finetunes the previous [ldm3d-4c](https://huggingface.co/Intel/ldm3d-4c) on 2 panoramic-images datasets:
|
| 20 |
+
- [polyhaven](https://polyhaven.com/): 585 images for the training set, 66 images for the validation set
|
| 21 |
+
- [ihdri](https://www.ihdri.com/hdri-skies-outdoor/): 57 outdoor images for the training set, 7 outdoor images for the validation set.
|
| 22 |
+
These datasets were augmented using [Text2Light](https://frozenburning.github.io/projects/text2light/) to create a dataset containing 13852 training samples and 1606 validation samples.
|
| 23 |
+
In order to generate the depth map of those samples, we used [DPT-large](https://github.com/isl-org/MiDaS) and to generate the caption we used [BLIP-2](https://huggingface.co/docs/transformers/main/model_doc/blip-2)
|
| 24 |
|
| 25 |
A demo using this checkpoint has been open sourced in [this space](https://huggingface.co/spaces/Intel/ldm3d)
|
| 26 |
|