Apply for community grant: Academic project (gpu)

#2
by hansen97 - opened

Project Title: YOND WebUI: Democratizing Practical Blind Raw Image Denoising

Description:

Hello Hugging Face team,

We are the authors of "YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency" (arXiv:2506.03645), and we are applying for a Community GPU Grant to support the deployment of our YOND WebUI—an open-source, Gradio-based platform for universal blind raw image denoising.

This initiative follows a direct invitation from your team. As Niels from the HF open-source team mentioned:

"I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability... It's great to see code is already available. Would you like to host the pre-trained [model] on https://huggingface.co/models?... You can also build a demo for your model on Spaces, we can provide you with a ZeroGPU grant, which gives you A100 GPUs for free."
Source: GitHub Issue #2 on YOND_public repository

We are now excited to accept this invitation. The GPU resources will be used to power a live Space that showcases YOND's core innovation: delivering state-of-the-art denoising for raw images from any camera, completely free from camera-specific data dependency. The WebUI will provide:

  • A live demo for users to process their own raw images.
  • An interactive showcase of our novel Coarse-to-Fine Noise Estimation (CNE) and SNR-Guided denoiser.
  • The foundation for hosting our models on the Hub and submitting the paper to hf.co/papers, creating a central hub for our work as Niels suggested.

This project embodies HF's mission to democratize AI. By providing this tool, we make advanced computational photography accessible to everyone, from researchers to photographers. We are eager to fully integrate our work into the Hugging Face ecosystem.

Thank you for your initial outreach and for your consideration of our grant application.

Key Links:

Hi @hansen97 , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.
If you can, we ask that you upgrade to Pro ($9/month) to enjoy higher ZeroGPU quota and other features like Dev Mode, Private Storage, and more: hf.co/pro

@hysts
Wow, thank you so much! That was incredibly fast—we really appreciate you approving the ZeroGPU grant for our Space.
We've seen the assignment and will start testing right away to make sure everything runs smoothly on ZeroGPU. This is a huge help for us and will let so many more people try out YOND's denoising.
We'll look into the Pro plan a bit later down the road as the project grows. Really appreciate the suggestion and all your support!

Sign up or log in to comment