diff options
Diffstat (limited to 'docs')
-rw-r--r-- | docs/filters.rst | 22 |
1 files changed, 19 insertions, 3 deletions
diff --git a/docs/filters.rst b/docs/filters.rst index 2abe2ea..8afd0cb 100644 --- a/docs/filters.rst +++ b/docs/filters.rst @@ -542,16 +542,20 @@ Non-local-means denoising Smoothing control parameter, should be around noise standard deviation or slightly less. Higher h results in a smoother image but with blurred - features. + features. If it is 0, estimate noise standard deviation and use it as + the parameter value. .. gobj:prop:: sigma:float - Noise standard deviation, improves weights computation. + Noise standard deviation, improves weights computation. If it is zero, + it is *not* automatically estimated as opposed to :gobj:prop:`h`. + :gobj:prop:`estimate-sigma` has to be specified in order to override + :gobj:prop:`sigma` value. .. gobj:prop:: window:boolean Apply Gaussian profile with :math:`\sigma = \frac{P}{2}`, where :math:`P` - is the gobj:prop:`patch-radius` parameter to the weight computation + is the :gobj:prop:`patch-radius` parameter to the weight computation which decreases the influence of pixels towards the corners of the patches. @@ -562,6 +566,13 @@ Non-local-means denoising no Gaussian profile used and from the nature of the fast algorithm, floating point precision errors might occur for large images. + .. gobj:prop:: estimate-sigma:boolean + + Estimate sigma based on [#]_, which overrides :gobj:prop:`sigma` + parameter value. Only the first image in a sequence is used for + estimation and the estimated sigma is re-used for every consequent + image. + .. gobj:prop:: addressing-mode:enum Addressing mode specifies the behavior for pixels falling outside the @@ -573,6 +584,11 @@ Non-local-means denoising International Symposium on Biomedical Imaging: From Nano to Macro, 2008, pp. 1331-1334. DOI:10.1109/ISBI.2008.4541250 + .. [#] + J. Immerkaer, *Fast noise variance estimation* in Computer vision and image + understanding 64.2 (1996): 300-302. DOI:10.1006/cviu.1996.0060 + + Horizontal interpolation ------------------------ |