Seeking industry insight on common pipeline bottlenecks

    Hi there fellow Mapcorians!

    We got a small group with some in depth knowledge in Deep learning AI, and we're thinking of ways to use it to smooth out any possible bumps in the development pipeline.

    As many of you here have a long history of industry experience, I'm hoping get your opinion on which parts of the game development pipeline you feel is the most cumbersome or could be called a major bottleneck?

    It can be from any discipline for example: audio, animation, texturing, modelling etc.


    Machine learning is rapidly evolving and will definitely become a integral part of the future tool set.

    I look forward to hearing you thoughts on the matter.


    Thank you in advance!

    If you can make a machine learning algorithm that can successfully fix unneeded header includes (and possibly reorganize to improve compile time) that would be amazing. I think the issue is that it would take too long to run. I've only ever discussed it in releation to genetic algorithms though as I don't really understand deep learning.

    Quote from Zarsky

    On 14/02/2018 at 2:24 PM, Zarsky said:

    There are people already doing research on that, but: procedural generation of content could benefit a lot from machine learning ( maybe use of the GAN techniques? ). You could also look into deep networks for aspect matching and rendering. (Aspect matching being about finding shader parameters to match the aspect of a material on a picture or more, and rendering about outputting pixels based on some parameters without having to render effectively the scene or one type of effect (there have been recent papers on cloud rendering using NNs and about denoising with neural networks (more useful for path tracers), maybe that could work for faster AA though (if you become millionaires with that,do quote me on that :P ) ) ).

    There is also work on animation and physics simulation, notably fast fluid simulation for games or hair simulation. ( it may be best fit for the first one though).

    (This is coming as a computer science and engineering student though)

    Dunno about bottlenecks, don't work in the industry but I've seen far too many UI/UX riddled with no clear coherence. How can this be that we apparently have to discover the same wheel every time it comes to this? There should be a standardized tool for that or at least a scaffold to build upon.

    Thanks for the input folks! We'll look into all possible solutions, and more suggestions are always welcome.


    Let me give you a few examples of how Neural networks will change animation tools:

    External Content www.youtube.com
    Content embedded from external sources will not be displayed without your consent.
    Through the activation of external content, you agree that personal data may be transferred to third party platforms. We have provided more information on this in our privacy policy.
    External Content www.youtube.com
    Content embedded from external sources will not be displayed without your consent.
    Through the activation of external content, you agree that personal data may be transferred to third party platforms. We have provided more information on this in our privacy policy.
    Remedy has also been busy developing new solutions:

    External Content www.youtube.com
    Content embedded from external sources will not be displayed without your consent.
    Through the activation of external content, you agree that personal data may be transferred to third party platforms. We have provided more information on this in our privacy policy.
    External Content www.youtube.com
    Content embedded from external sources will not be displayed without your consent.
    Through the activation of external content, you agree that personal data may be transferred to third party platforms. We have provided more information on this in our privacy policy.

    There's also plenty more in other areas, which I'll post later.

    As you can see, at this very early stage, Deep learning can already do some pretty impressive stuff. Research in this department is rapidly growing and I've seen big game companies hiring bunch of researchers to make use of that potential.

    Quote from WD

    On 2/19/2018 at 10:48 PM, WD said: Dunno about bottlenecks, don't work in the industry but I've seen far too many UI/UX riddled with no clear coherence. How can this be that we apparently have to discover the same wheel every time it comes to this? There should be a standardized tool for that or at least a scaffold to build upon.

    UX is probably due to opinion.

    Scaleform is no more so we're in a bit of a weird time. There's not a really good solution right now (scaleform wasn't great but it could at least accomplish the job).

Participate now!

Don’t have an account yet? Register yourself now and be a part of our community!

Register Yourself Login