DFM

(★ 167)

Implementation of "Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision"

File Explorer

- - CO3D.yaml
  - CO3DPN.yaml
  - realestate.yaml
- - local.yaml
  - online.yaml
- config.yaml
- - __init__.py
  - json_index_dataset.py
  - json_index_dataset_map_provider_v2.py
- __init__.py
- co3d_new.py
- realestate10k.py
- dependency_links.txt
- PKG-INFO
- SOURCES.txt
- top_level.txt
- __init__.py
- denoising_diffusion_pytorch.py
- pixelnerf_trainer.py
- version.py
- co3d_results.py
- re_results.py
- train_3D_diffusion.py
- train_pixelnerf.py
- teaser.gif
- - DiT.py
- __init__.py
- pixelnerf_encoders.py
- pixelnerf_helpers.py
- pixelnerf_model.py
- pixelnerf_model_cond.py
- renderer.py
- resnet.py
- resnetfc.py
- resnetfc_time_embed.py
- view_interpolation.py
- re_indices.py
.gitignore
geometry.py
layers.py
losses.py
README.md
requirements.txt
setup.py
utils.py

1. Get the code

git clone https://github.com/ayushtewari/DFM

Downloads the entire project code from GitHub to your computer.

cd DFM

Moves into the project folder you just downloaded.

Easy Recommended

Prerequisites

pip install torch==2.0.1 torchvision

Installs the package published on PyPI directly — no need to clone the source.

pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py39_cu117_pyt201/download.html

Installs the package published on PyPI directly — no need to clone the source.

✅ After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.

Pulled directly from this repo's README.

Easy

Prerequisites

pip install torch==2.0.1 torchvision

Installs the package published on PyPI directly — no need to clone the source.

pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py39_cu117_pyt201/download.html

Installs the package published on PyPI directly — no need to clone the source.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.