Spaces:
Running on Zero
Running on Zero
|
Download README.md from hugging-apps/diffcve-2607: direct link, hf CLI and curl.
- Browser
- Download file 1.59 kB
-
https://huggingface.co/spaces/hugging-apps/diffcve-2607/resolve/main/README.md
- Command line
-
hf download hf://spaces/hugging-apps/diffcve-2607/README.md
-
curl -L -o README.md https://huggingface.co/spaces/hugging-apps/diffcve-2607/resolve/main/README.md
1.59 kB
metadata
title: DiffCVE
emoji: 🎬
colorFrom: red
colorTo: yellow
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
python_version: '3.12'
short_description: Diffusion-based compressed video enhancement
startup_duration_timeout: 1h
DiffCVE: Diffusion-based Compressed Video Enhancement
Interactive demo of DiffCVE (paper · code · model) — a diffusion-based restoration model for H.264-compressed video.
Upload a clip, choose an H.264 quantization parameter (QP), and the demo:
- compresses your video with the paper's own fixed-QP JM (H.264) encoder,
- extracts the coding priors the bitstream carries — per-pixel motion vectors (quarter-luma-pixel units) and luma prediction residuals,
- restores the clip with the single-step distilled diffusion model, conditioned on those priors, the VAE-encoded structure, and a QP-conditioned degradation prompt (CDSP),
- decodes with the coding-prior-weighted fusion (CPWF) VAE decoder.
Everything runs on ZeroGPU; frames are capped (≤10) and large videos are downscaled (≤720 px) so a run finishes in about a minute and a half.
Notes
- The bundled
codec/encoder/codec/decoderbinaries are the authors' modified JM (ITU/ISO) reference codec builds; copyright notices are included incodec/COPYRIGHT_*.txt. - Example clips are from
linoyts/repo-to-space-example-videos(CC0-1.0).