README.md

metadata

title: ReSWD
emoji: 📊
colorFrom: purple
colorTo: green
sdk: gradio
sdk_version: 5.47.1
app_file: app.py
pinned: false
short_description: Distribution Matching for Color Guidance and Correction.
models:
  - stabilityai/stable-diffusion-3.5-large-turbo
license: other
license_name: stabilityai-ai-community
license_link: LICENSE.md

ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.

This is the official codebase for ReSWD, a state-of-the-art algorithm for distribution matching with reduced variance. It has several applications (such as diffusion guidance or color matching).

• Repository: https://github.com/Stability-AI/ReSWD
• Tech report: https://arxiv.org/pdf/2510.01061
• Video summary: https://youtu.be/ckcSgf0s-jI
• Project page: https://reservoirswd.github.io/
• arXiv page: https://arxiv.org/abs/2510.01061

Citation

@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}
}