Algorithmic Beautification of Selfies | Two Minute Papers #159

TL;DR

This video explains how researchers have developed a technique to adjust the camera distance and beautify selfie photos using algorithmic computations and 3D modeling.

Transcript

Dear Fellow Scholars, this is Two Minute Papers with Károly Zsolnai-Fehér. Today we're going to talk about a rigorous scientific topic, none other than the creation of the perfect selfie photo. By definition selfies are made by us, which means that these are typically short-range photos, and due to the perspective distortion of the camera lens, we ... Read More

Key Insights

• 📷 Selfie photos often have perspective distortions due to short camera distances.
• 📷 The algorithmic beautification technique involves analyzing the photo, creating a digital model of the perspective camera, and adjusting the camera distance to correct distortions.
• 😀 A 3D model of the face allows for additional enhancements like rotation.
• 😀 Well-recognizable hotspots on the face are used to create an accurate 3D representation.
• 🥡 The technique can be evaluated by comparing its output with ground truth images taken at different camera distances.
• ❓ The technique has been made available as an interactive version online.
• 🤗 The research opens up possibilities for automated techniques to create the perfect selfie photo.

Questions & Answers

Q: How does the algorithmic beautification technique work?

The technique involves analyzing a selfie photo, creating a digital model of the perspective camera, and using mathematical fitting to find an appropriate camera setup that would result in the given photo. The distance can then be adjusted to correct lens distortions.

Q: What other enhancements can be done with the digital 3D model of the face?

Apart from adjusting the camera distance, the 3D model allows for the rotation of the face in multiple directions, enabling further improvements to the selfie photo.

Q: How are well-recognizable hotspots on the face used in creating the 3D model?

Hotspots on the face, such as the chin, eyebrows, nose stem, and eyes, are used to create a 3D representation of the human face. Additional hotspots are added to improve the accuracy of the model.

Q: How can the algorithmic technique be evaluated?

The technique can be evaluated by comparing the output of the algorithm on selfie photos with the ground truth images taken from different camera distances. Difference images can be used to visualize any errors or discrepancies.

Summary & Key Takeaways

• Selfie photos often have perspective distortions, such as magnification of the nose and forehead, due to the short camera distance.

• The technique described in the video analyzes the photo, creates a digital model of the perspective camera, and adjusts the camera distance to correct distortions.

• By creating a 3D model of the face, additional enhancements like rotation can be applied to improve the overall selfie photo.