Sign in to confirm you’re not a bot
This helps protect our community. Learn more

Variational Methods for Computer Vision - Lecture 7 (Prof. Daniel Cremers)

cvprtum
14.2K subscribers

The Euler Lagrange Equation

0:15

Inverse Problems and Image Restoration

1:18

Inverse Problems

2:57

Problem of Inference

3:35

Image Restoration

7:21

The Image Denoising

8:14

Euler Lagrange Equation

11:53

Gradient Descent

13:13

Nonlinear Diffusion

14:16

Variations of Total Variation for Color

16:22

Bayesian Inference

26:12

Conditional Probability

28:39

The Maximum A-Posteriori Estimation

29:49

Likelihood

30:20

Most Likely Configuration

32:02

Rewriting the Likelihood

41:09

Markov Property

42:21

Poisson Noise Model

47:02

Bayesian Formula

47:32

Variational Energy Minimization

51:23

Motion Blur

55:58

Example of Motion Blur

1:02:13

Blur Models

1:03:24

Pinhole Camera in Principle

1:04:46

D Focus Blur

1:06:41

Autofocus

1:10:32

Geometric Reconstruction

1:19:57

Super Resolution

1:21:46

Variational Approach

1:26:57

Performance Evaluation

1:30:38
Variational Methods for Computer Vision - Lecture 7 (Prof. Daniel Cremers)
53Likes
9,873Views
2013Nov 13
Lecturer: Prof. Dr. Daniel Cremers (TU München) Topics covered:
  • Rudin Osher Fatemi (ROF) Model for Denoising
  • Variational Image Deblurring
  • Baysian Inference and Inverse Problems
  • Video Super Resolution
Lecture slides: https://vision.in.tum.de/teaching/onl...

Follow along using the transcript.

cvprtum

14.2K subscribers