Instructions to use zeyuren2002/EvalMDE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zeyuren2002/EvalMDE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zeyuren2002/EvalMDE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Depth-to-Normal
We generated our meta-dataset by collecting RGB-D datasets and converting the depth maps into surface normal maps.
We took PlaneSVD from Klasing et al. and added a few modifications to handle depth discontinuties. We encourage you to try using other algorithms as it can potentially improve the quality of the ground truth and hence the performance of the model.
Please see notes/depth_to_normal.ipynb for example usage.