View source for Samsung electronics co., ltd. (20240096011). METHOD FOR RENDERING RELIGHTED 3D PORTRAIT OF PERSON AND COMPUTING DEVICE FOR THE SAME simplified abstract

=METHOD FOR RENDERING RELIGHTED 3D PORTRAIT OF PERSON AND COMPUTING DEVICE FOR THE SAME=


==Organization Name==

[[:Category:samsung electronics co., ltd.|samsung electronics co., ltd.]]


[[Category:samsung electronics co., ltd.]]

==Inventor(s)==

[[:Category:Artem Mikhailovich Sevastopolskiy of Moscow (RU)|Artem Mikhailovich Sevastopolskiy of Moscow (RU)]][[Category:Artem Mikhailovich Sevastopolskiy of Moscow (RU)]]

[[:Category:Victor Sergeevich Lempitsky of Moscow (RU)|Victor Sergeevich Lempitsky of Moscow (RU)]][[Category:Victor Sergeevich Lempitsky of Moscow (RU)]]

==METHOD FOR RENDERING RELIGHTED 3D PORTRAIT OF PERSON AND COMPUTING DEVICE FOR THE SAME - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240096011 titled 'METHOD FOR RENDERING RELIGHTED 3D PORTRAIT OF PERSON AND COMPUTING DEVICE FOR THE SAME

==Simplified Explanation==

The disclosure provides a method for generating relightable 3D portraits using a deep neural network and a computing device implementing the method. The method allows for obtaining realistically relighted 3D portraits in real-time on computing devices with limited processing resources, achieving high-quality results without the need for complex and costly equipment.

* Method for rendering a relighted 3D portrait:
  * Receiving input defining camera viewpoint and lighting conditions
  * Rasterizing latent descriptors of a 3D point cloud at different resolutions based on the camera viewpoint
  * Processing rasterized images with a deep neural network to predict albedo, normals, environmental shadow maps, and segmentation mask
  * Fusing predicted albedo, normals, environmental shadow maps, and segmentation mask into the relighted 3D portrait based on lighting conditions

---

### Potential Applications
* Virtual reality experiences
* Digital art and animation
* Personalized avatars for gaming or social media platforms

### Problems Solved
* Real-time relighting of 3D portraits
* High-quality results without complex equipment
* Efficient use of limited processing resources

### Benefits
* Realistic relighted 3D portraits
* Cost-effective solution
* Improved user experience in various applications

### Potential Commercial Applications
#### Optimizing 3D Portrait Rendering for Real-time Applications

---

#### What are the technical specifications of the computing device required to implement this method effectively?
To implement this method effectively, the computing device should have sufficient processing power to run the deep neural network efficiently. Additionally, it should have the capability to handle real-time rendering of 3D images and support the rasterization process required for generating the relighted portraits.

#### How does this method compare to traditional methods of relighting 3D portraits in terms of speed and quality of results?
This method offers real-time relighting of 3D portraits with high-quality results, even on computing devices with limited processing resources. Traditional methods may require complex equipment and longer processing times to achieve similar results.


==Original Abstract Submitted==

the disclosure provides a method for generating relightable 3d portrait using a deep neural network and a computing device implementing the method. a possibility of obtaining, in real time and on computing devices having limited processing resources, realistically relighted 3d portraits having quality higher or at least comparable to quality achieved by prior art solutions, but without utilizing complex and costly equipment is provided. a method for rendering a relighted 3d portrait of a person, the method including: receiving an input defining a camera viewpoint and lighting conditions, rasterizing latent descriptors of a 3d point cloud at different resolutions based on the camera viewpoint to obtain rasterized images, wherein the 3d point cloud is generated based on a sequence of images captured by a camera with a blinking flash while moving the camera at least partly around an upper body, the sequence of images comprising a set of flash images and a set of no-flash images, processing the rasterized images with a deep neural network to predict albedo, normals, environmental shadow maps, and segmentation mask for the received camera viewpoint, and fusing the predicted albedo, normals, environmental shadow maps, and segmentation mask into the relighted 3d portrait based on the lighting conditions.



[[Category:G06T15/60]]
[[Category:G06F18/214]]
[[Category:G06N3/084]]
[[Category:G06T7/194]]
[[Category:G06T15/04]]
[[Category:G06T15/10]]
[[Category:G06T17/20]]