Learning Robust Imaging Models without Paired Data
Offered By: Society for Industrial and Applied Mathematics via YouTube
Course Description
Overview
Syllabus
Intro
Outline
Linear approximation for imaging process
The error effects
Model based approaches
Deep learning (DL) based approaches
Data bottleneck in DL
Data collection in video superresolution
Goal of the talk
Image denoising
The basic idea
Model formulation
Numerical method
One remark on overfitting issue
Quantitative results for real noisy images
Qualitative results
Latent space verification
Real-world noisy images from Huawei
Image segmentation
Probabilistic model
Examples
Deep CV model
Distributions in latent space
Motivation
The case of unpaired datasets
Unpaired degradation modeling
The idea
The loss function
Inference invariant condition
Synthetic noisy images
Experiments
Visual results
Summary
Taught by
Society for Industrial and Applied Mathematics
Related Courses
Upscaling and Automation - New Opportunities for Multiscale Systems ModelingSociety for Industrial and Applied Mathematics via YouTube Supercomputing Spotlights - Supercomputing Software for Moore and Beyond
Society for Industrial and Applied Mathematics via YouTube Online Parallel Paging and Green Paging
Society for Industrial and Applied Mathematics via YouTube The Adoption of Blockchain-Based Decentralized Exchanges
Society for Industrial and Applied Mathematics via YouTube Model Invariants and Functional Regularization
Society for Industrial and Applied Mathematics via YouTube