Looking at the picture below, you may think it's just a picture in real life.
Now in many games, we can see the game scenes with exquisite picture quality and gorgeous special effects.
Recently, researchers at Intel Labs are thinking about how to use machine learning,It can make the rendered game screen look closer to the real world.If this technology can be implemented and put into wide use, it may improve the game image quality to a new level.
In the summary of this Intel project, how to enhance the synthetic image by convolutional neural network (a deep learning algorithm) is described.
The team will train the neural network with the information from the game's rendered image and the middle rendering buffer (g buffer);
This intermediate render buffer provides information about the geometry, materials, and lighting in the scene,And it is used as the input of image enhancement network modulation image features. Finally, through the image enhancement network, it forms a picture similar to the real life vision.
However, there are still some problems with this technology. For example, the license plate becomes blurred, the color is paler compared with the rest of the video, and there are still some differences between the color in reality.
All in all, the Intel project is very important for the game industry,In particular, the development of game image quality has certain progressive significance, which means that the game field can make full use of deep learning technology to improve the game experience.
At present, DLSS technology of supersampling deep learning and RTX ray tracing technology of simulating real ray rendering have been widely used. If this project of Intel can be successfully implemented in the future,In the future, there may be an unprecedented visual subversion in the field of games or vr virtual reality.
- THE END -
Link to the original text:Pacific computer network