0

We are working on a complex system, which will take data from a game, process it via machine learning methods (think types of neural networks (NN)) and output an enhanced image.

The enhancement varies quite a bit depending on the scenario - super resolution, image-to-image translation (e.g. removing objects from the background or completely converting an image from one domain to another (think DALL-E)) and so on. All NNs can be measured with some sort of metric (PSNR, SSIM, FID and so on). However those do not measure the realism perception of the viewer of the final imagery. In fact there are many cases, where metrics show top scores yet the viewers would dismiss the imagery and label it as "unrealistic" withing milliseconds.

One example for an attempt to "add realism" can be seen here - the Photorealism Enhancement project led by Intel. While the result looks more visually appealing (for me at least) I am looking for an actual quantifiable way to measure how the viewer perceives the result.

I looked into an old paper called Measuring the Perception of Visual Realism in Images where they introduce the so called Realism Response Rating. I am hoping that someone here can point me to more current research or examples.

PS: I know that realism is sort of subjective hence cannot be 100% accurately measured. :P

7
  • Can't judge the methods in the paper you mentioned because of a paywall. Can elaborate whether there is, in your opinion, something else wrong with Realism Response Rating other than it is "old"? Commented Aug 26, 2022 at 9:39
  • I'm not sure this is a UX question - feels more like Psychology or art to me - there's no "User Experience" element to this. You're not asking if the user will benefit from a more realistic image - You're asking for a subjective image evaluation. Commented Aug 26, 2022 at 10:41
  • do you mean something like researchgate.net/publication/… ? if so you can download it for free
    – Devin
    Commented Aug 26, 2022 at 14:02
  • @RouxMartin The evaluation will be conducted on people, who are using a simulator for training. The degree of perception and proximity to "realism" will determine how close the simulation is (in terms of visuals) to a real life scenario. Commented Aug 29, 2022 at 8:02
  • 1
    I’m voting to close this question because This is a question about general psychology and is not about user experience. Commented Aug 29, 2022 at 14:57

1 Answer 1

0

The only thing I am aware of when it comes to the understanding of 'realism' is the concept of 'uncanny valley' that is used to describe the different degrees of emotional response to a stimuli that relates to human-likeness.

But I think you can apply a similar approach where you can chart a range of emotional responses and try to see if there is some pattern or grouping that describes the general range and degree of responses that you capture.

enter image description here

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.