Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Signal Processing Course: Denoising
Search
Gabriel Peyré
January 01, 2012
Research
1.5k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Signal Processing Course: Denoising
Gabriel Peyré
January 01, 2012
More Decks by Gabriel Peyré
See All by Gabriel Peyré
IA for theory
gpeyre
1
560
The mathematics of transformers
gpeyre
1
590
Computational OT #4 - Gradient flow and diffusion models
gpeyre
1
1.2k
Computational OT #1 - Monge and Kantorovitch
gpeyre
0
1.4k
Computational OT #2 - Entropic regularization
gpeyre
0
600
Computational OT #3 - Dual and semidiscrete
gpeyre
1
430
Optimal and Diffusion Transports in Machine Learning
gpeyre
0
2.6k
The Mathematics of AI
gpeyre
1
2.6k
Transformers are Universal in Context Learners
gpeyre
0
1.1k
Other Decks in Research
See All in Research
Être éleveur dans un monde en transition : Comprendre les changements pour mieux les accompagner
institutdelelevage
PRO
0
160
Local Development Companies Network - National Conference 2026
ldcn
0
160
[CV勉強会@関東 CVPR2026] PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow / kantocv 67th CVPR 2026
shunk031
0
400
CDCL を用いた MILP の厳密解法
imai448
0
330
オンライン凸最適化の基礎とゲーム理論への応用 (IBIS 2026 チュートリアル)
taira_tsuchiya
2
1.4k
論文読み会 SNLP2026 Tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment
s_mizuki_nlp
0
330
Développer des solutions de réduction des émissions de méthane entérique : 1ers résultats Méthane 2030
institutdelelevage
PRO
0
280
Kunai: Toward a Verifier-Safe Layered DSL for Nested Encapsulation Packet Filtering on eBPF
takehaya
1
190
実例から見るLLMのマンガ理解:実務VQAタスクによる長期的文脈と視覚情報の定性評価
kzmssk
0
220
最先端NLP 2026 論文紹介: Wait, Wait, Wait... Why Do Reasoning Models Loop? / SNLP Paper Review: Wait, Wait, Wait... Why Do Reasoning Models Loop?
tkng
0
270
山中市政が招いた組織崩壊:よこはま安心ボックスを例に
sishi
0
370
Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
satai
3
190
Featured
See All Featured
Raft: Consensus for Rubyists
vanstee
143
7.9k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
6.2k
SEO Brein meetup: CTRL+C is not how to scale international SEO
lindahogenes
2
3k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
18k
Utilizing Notion as your number one productivity tool
mfonobong
4
640
Code Review Best Practice
trishagee
74
20k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.6k
The Pragmatic Product Professional
lauravandoore
37
7.5k
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
74
43k
Game over? The fight for quality and originality in the time of robots
wayneb77
1
330
How to make the Groovebox
asonas
2
2.5k
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.4k
Transcript
Linear and Non Linear Denoising Gabriel Peyré www.numerical-tours.com
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Noise in Images
Denoising Problem
Denoising Problem
Additive Noise Model
Noise Distributions −0.3 −0.2 −0.1 0 0.1 0.2 0.3 −0.3
−0.2 −0.1 0 0.1 0.2 0.3
Noise Distributions −0.3 −0.2 −0.1 0 0.1 0.2 0.3 −0.3
−0.2 −0.1 0 0.1 0.2 0.3
Noise Distributions −0.3 −0.2 −0.1 0 0.1 0.2 0.3 −0.3
−0.2 −0.1 0 0.1 0.2 0.3
Data-dependent Noise
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Linear Denoising Estimator
Fourier and Denoising
Optimal Filter Choice
Oracle Estimation of Optimal Filter
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Diagonal Thresholding
Wavelet Diagonal Hard Thresholding
Sparse Signal Estimation
Optimal Threshold Selection
W unit variance white noise. Non-linear Approximation and Estimation
Hard vs. Soft Thresholding
Hard vs. Soft Thresholding
Optimal Threshold
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Translation Invariant Denoising
Translation Invariant Wavelets
Translation Invariant Haar (1D)
Translation Invariant Transform (2D)
Translation Invariant Thresholding
Optimal Invariant Threshold
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Between Hard and Soft Thresholding
Stein Quadratic-Soft Thresholder
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Block Thresholding
Optimal Block Choice
Comparison
Overview • Noise in Signals and Images • Linear Denoising
by Blurring • Non-linear Wavelet Denoising • Translation Invariant Thresholding • Other Diagonal Thresholders • Non-diagonal Block Thresholding • Data-dependent Noise
Poisson Noise
Poisson Noise Variance Stabilization 1 2 3 4 5 6
7 8 9 10 0.75 0.8 0.85 0.9 0.95 1 1.05
Multiplicative Noise
Multiplicative Noise Stabilization 0 0.5 1 1.5 2 2.5 −1.5
−1 −0.5 0 0.5 1 1.5
Conclusion