- Notifications
You must be signed in to change notification settings - Fork1
Variance reduction for Sliced Wasserstein Distance using Reservoir Sampling.
License
Stability-AI/ReSWD
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.
This is the official codebase forReSWD, a state-of-the-art algorithm for distribution matching with reduced variance. It has several applications (such as diffusion guidance or color matching).
The project usesuv for package management. Install it viapip install uv if not installed.
Then run
uv sync
We support a CLI and gradio demo. The cli can be run with:
uv run -m src
It will then guide you through the different modes
The gradio demo can be executed with
uv run -m src.gradio_demo
Inexample/test_frames_with_color_patches we have uploaded the test frames, including the mean swatch values from a color checker for error calculations.
@article{boss2025reswd,title={ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.},author={Boss, Mark and Engelhardt, Andreas and Donné, Simon and Jampani, Varun},journal={arXiv preprint},year={2025}}
About
Variance reduction for Sliced Wasserstein Distance using Reservoir Sampling.
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Uh oh!
There was an error while loading.Please reload this page.