(Scattering Network) is a MATLAB software which includes scattering transforms of one-dimensional signals and images, with applications to classifications of audio signals, multifractals and images. It includes demos which reproduce the figures of our publications.
is a pointer to tutorials to teach how to perform the scattering transform.
You can fill in the following form
to get the latest updates.
Softwares released by the team
||Date of release
||L. Sifre, J. Anden
||[Andén and Mallat, 2011b] , [Sifre and Mallat, 2013]
||[Oyallon and Mallat, 2015]
||Requires to be an advanced user of ScatNet
||Minimalist version of the scattering transform (e.g. for pedagogical purposes)
||X. Cheng, X. Chen (Mia)
||[Chen et al., 2014]
||[d'Aspremont et al., 2015]
||32 bits precision, triangular kernels, multicore and in-place. Speed up calculations and reduce memory
Note that these packages are provided for legacy purposes. However, links and articles can be missing. To compute scattering transforms, please use the ScatNet toolbox above.
Image scattering toolbox v3 :
Released July 11 2012.
A scattering transform toolbox for one-dimensional signals with support for audio scattering described in
1D software (version 1.02, released June 15th, 2012).
Bag-of-frames affine space classifier for arbitrary feature representations, as described in reference :
classifier (released June 15th, 2012).
Scattering transform of images with the
classification algorithm described in reference 
(Updated version march 2011):
Containing matlab code corresponding
to numerical experiences and figures from the paper .
2D software (new version).
Containing rotation invariant scattering from paper