VapourSynth denoising functions
Project description
vs-denoise
VapourSynth denoising, regression, and motion-compensation functions
Wrappers for denoising, regression, and motion-compensation-related plugins and functions.
For support you can check out the JET Discord server.
How to install
Install vsdenoise
with the following command:
pip install vsdenoise
Or if you want the latest git version, install it with this command:
pip install git+https://github.com/Jaded-Encoding-Thaumaturgy/vs-denoise.git
Example usage
from vsdenoise import MVTools, SADMode, MotionMode, Prefilter, BM3DCuda, Profile, nl_means
clip = ...
ref = MVTools.denoise(
clip, thSAD=100, block_size=32, overlap=16,
motion=MotionMode.HIGH_SAD,
prefilter=Prefilter.DFTTEST,
sad_mode=(
SADMode.ADAPTIVE_SPATIAL_MIXED,
SADMode.ADAPTIVE_SATD_MIXED,
)
)
denoise = BM3DCuda.denoise(
clip, sigma=0.8, tr=2, profile=Profile.NORMAL, ref=ref, planes=0
)
denoise = nl_means(denoise, tr=2, strength=0.6, ref=ref, planes=[1, 2])
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vsdenoise-2.5.1.tar.gz
(63.5 kB
view hashes)
Built Distribution
vsdenoise-2.5.1-py3-none-any.whl
(72.1 kB
view hashes)
Close
Hashes for vsdenoise-2.5.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e699bacf59444d23f17c9877a513b76756bebdcf57d4132679a96fa8700f03f4 |
|
MD5 | a57c40f0fd4995cf40e2eaedcc1e8fa6 |
|
BLAKE2b-256 | 8c690e4b5d6d8822c15cb5d9f677169065553eb035f1cfc403f5131af6fc2651 |