Threads
- Intel has developed a new open-source AI tool that can objectively analyze game visuals to measure the impact of upscalers in real time.
- The researchers trained AI on a large dataset with artifacts caused by upscalers to match the prowess of human perception.
- The tool can help gamers better understand how upscalers affect visuals and let developers further improve these technologies.
With the emergence of upscaling technologies creating AI-generated artificial frames, issues like ghosting and aliasing have become all too common in visuals. However, a new Intel tool can help detect these anomalies much more easily.
Intel has developed a new AI tool that can objectively analyze image quality and measure the impact upscalers have on visuals in real time. A large dataset involving 20 participants was fed to the AI to help it match human perception in finding these anomalies.
Why it matters: The new AI tool by Intel is a great step towards objectively assessing game visuals, and its open-source nature means that developers can customize and expand upon it to automate detecting visual anomalies caused by upscalers for their projects.
As explained by Intel, the tool dubbed CGVQM (Computer Graphics Visual Quality Metric) can capture ‘complex artifacts introduced by modern rendering techniques.’ It is also able to detect how much each anomaly affects a certain part of the visuals.
By combining high accuracy, interpretability, and generalizability, CGVQM provides a powerful new tool for graphics researchers and game developers to evaluate rendering quality as perceived by an end user without the need for costly human studies.
The tool outperformed all state-of-the-art metrics in predicting human ratings so far, which means that it is also accurate enough for game developers to use. This could help developers further correct visual anomalies caused by upscalers and improve those technologies.
By analyzing how perceptual quality degrades across different input resolutions and upscaling configurations, developers can determine the sweet spot, where performance gains are maximized with minimal visual compromise.
On the flip side, it can also help gamers select optimal quality settings in games because it can show at what level the image quality begins to drop noticeably.
Do you think the new AI tool will help developers better measure the effects of upscalers on game visuals? Let us know your thoughts in the comments below, or join the discussion on the Tech4Gamers forum.
Thank you! Please share your positive feedback. 🔋
How could we improve this post? Please Help us. 😔
Shameer Sarfaraz has previously worked for eXputer as a Senior News Writer for several years. Now with Tech4Gamers, he loves to devoutly keep up with the latest gaming and entertainment industries. He has a Bachelor’s Degree in Computer Science and years of experience reporting on games. Besides his passion for breaking news stories, Shahmeer loves spending his leisure time farming away in Stardew Valley. VGC, IGN, GameSpot, Game Rant, TheGamer, GamingBolt, The Verge, NME, Metro, Dot Esports, GameByte, Kotaku Australia, PC Gamer, and more have cited his articles.
Join Our Community
