Tools

Search

Explore

Videos Channels Figures

Atmrix

About

Tools

Search

Explore

Videos Channels Figures

Atmrix

About

CS

Carola Schönlieb

05/10/18

@ Y Combinator

My PhD focused on image restoration, specifically using differential equations to solve problems similar to those addressed by Photoshop's content-aware fill.

Video

YC

Mathematical Approaches to Image Processing with Carola Schönlieb

@ Y Combinator

Mathematical Approaches to Image Processing with Carola Schönlieb

05/10/18

Related Takeaways

CS

Carola Schönlieb

05/10/18

@ Y Combinator

The technique used for image restoration is similar to the content-aware fill feature in Photoshop, but it predates Photoshop's development.

CS

Carola Schönlieb

05/10/18

@ Y Combinator

During my research, I discovered that the Cahn-Hilliard equation was used for image restoration, which involves replacing damaged parts of a digital image with suggested content from surrounding areas.

CS

Carola Schönlieb

05/10/18

@ Y Combinator

In my postdoc, I shifted towards inverse imaging problems, where the observed data is not a direct image but a transform, such as in CT scans.

CS

Carola Schönlieb

05/10/18

@ Y Combinator

I started my research in mathematics in Vienna, focusing on partial differential equations, which model various natural phenomena in physics and biology.

JL

Joan Lasenby

09/17/18

@ Y Combinator

One of my early projects involved translating classical projective geometry concepts into geometric algebra, which simplified the mathematical complexity of computer vision tasks.

CS

Carola Schönlieb

05/10/18

@ Y Combinator

Successful image denoising methods focus on preserving edges, which are crucial for maintaining the integrity of the image's features.

CS

Carola Schönlieb

05/10/18

@ Y Combinator

For those interested in image processing, I recommend starting with foundational books and exploring recent research from institutions like UCLA.

JL

Joan Lasenby

09/17/18

@ Y Combinator

I collaborated with a motion capture company to develop algorithms for camera calibration, leveraging the unique properties of geometric algebra to enhance the process.

CS

Carola Schönlieb

05/10/18

@ Y Combinator

In collaborations with hospitals, we focus on developing algorithms that maximize the quality of high-resolution images from limited data, particularly in medical imaging.