Contents
The Ai Denoiser can also be run from the command line on frames that have already been rendered to disc.
$RMANTREE/bin/denoise_batch
usage: denoise run [-h] [-v] [-a ASYMMETRY] [-o OUTPUT] [-cf] [-f] [-j]
files [files ...]
positional arguments:
files
Image files to be denoised. Can accept a glob as input. Ex: foo.*.exr
$RMANTREE/bin/denoise_batch -h
usage: denoise run [-h] [-v] [-a ASYMMETRY] [-o OUTPUT] [-cf] [-f] [-j]
files [files ...]
positional arguments:
files Image files to be denoised. Can accept a glob as input. Ex: foo.*.exr
optional arguments:
-h, -h, show this help message and exit
-v, --verbose Verbose output for debugging.
-a ASYMMETRY, --asymmetry ASYMMETRY
controls the asymmetry value, 0 is the best quality,
higher values encourage the denoiser to avoid
over blurring, leading to weaker denoising.
-o OUTPUT, --output OUTPUT
The output directory for the denoised images. The JSON
config file(s) will also be written to this directory.
If not specified, we write into a subdirectory called
"denoised", from the image path.
-cf, --crossframe Do crossframe denoising
-f, --flow Whether to compute optical flow.
-j, --json If provided, use the first input file as the
configuration JSON file. All other files and options
are ignored.
-h, | -h, | show this help message and exit |
---|---|---|