Machine Learning meets Computational Photography

2D and 3D Multiscale Geometric Transforms

author: Jean-Luc Starck, LCS - Laboratoire de Cosmologie et Statistiques, French Alternative Energies and Atomic Energy Commission (CEA)
published: Jan. 23, 2012, recorded: December 2011, views: 304

Slides

Slides
0:00	To Be Announced
0:28	Audience´s Choice
1:35	2D and 3D Multiscale Geometric Transforms
1:43	What is a good sparse representation for data?
1:58	Local DCT / Wavelet transform / Curvelet transform
2:40	Morphological Diversity
3:36	Wavelets and edges
4:18	SNR = 0.1 - 1
4:30	SNR = 0.1 - 2
4:56	Undecimated Wavelet Filtering (3 sigma)
5:05	Ridgelet Filtering (5sigma)
5:41	Continuous Ridgelet Transform
6:02	The ridgelet coefficients of an object f are given by analysis
6:54	Ridgelet Transform
7:17	Local Ridgelet Transform
7:51	Poisson Noise and Line-Like Sources Restoration (MS-VST + Ridgelet)
8:15	The Curvelet Transform (CUR01)
9:08	NGC2997
9:10	Undecimated Isotropic WT
9:16	Partitioning
9:21	The Fast Curvelet Transform
10:01	The Curvelet Transform
10:10	Contrast Enhancement Using The Curvelet Transform
11:04	Contrast Enhancement - 1
11:11	Contrast Enhancement - 2
11:13	Contrast Enhancement - 1
11:15	Contrast Enhancement - 2
11:21	Deconvolution
11:56	3D Multiscale Geometric Transforms
12:10	3D Wavelets
12:21	3D extension of Curvelet
12:42	3D beamlet transform
13:43	Discrete 3D Beamlet transform
14:15	Discrete 3D BeamCurvelet transform
14:54	3D BeamCurvelets - 1
15:01	3D BeamCurvelets - 2
15:29	3D ridgelet transform
15:45	3D Discrete ridgelet transform
16:16	Discrete 3D RidCurvelet transform
16:28	3D RidCurvelets
16:31	Denoising
17:02	3D Plane detection level
17:38	3D Line detection level
17:52	Combined denoising
18:19	Combined denoising results - 1
18:26	Combined denoising results - 2
18:55	Fast second generation 3D curvelets - 1
19:33	Fast second generation 3D curvelets - 2
20:35	Fast second generation 3D curvelets - 3
20:39	Fast second generation 3D curvelets - 4
20:57	Example: denoising
21:22	Example: video denoising
21:41	Example: hyperspectral data denoising
21:54	Sparse component separation
22:32	Results
23:23	Inpainting - 1
23:48	Inpainting - 2
24:06	Inpainting - 3
24:21	Inpainting - 4
24:25	Inpainting - 5
24:34	Conclusions

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.