• 0 Posts
  • 33 Comments
Joined 11 months ago
cake
Cake day: December 22nd, 2023

help-circle





  • Just to add some information, what’s innovative here is that they are likely using a traditional machine learning model (eg: neural networks) to identify the corners of the screen and infer the position the gun is aiming at from this.

    Sinden is aiming to do the same thing, but using older techniques known as compute vision. It adds a white border around the screen and uses those CV algorithms to find this rectangle. It is not AI at all.

    The reason Sinden is doing this is because it is much more easier this way (and so it is fast to compute, and very accurate).

    Whatever AI they use, it will likely be either less accurate and/or be very slow (imagine situations with low ambient light and the screen turning black). I have seen a review in japanese from journalists who tried it, and the response time was not great (and the team wants to divide it by 2 before release, which will still be worse than Sinden).

    Another possibility could be there is no AI at all, and they exploit specificities of Time Crisis. When you shoot, the screen goes white for 1 or 2 frames. You don’t need AI to spot this frame and do something very similar to Sinden without using any border.

    At this point, it might be too late to move the « cursor » to the right location, but emulators nowadays are able to apply inputs in the past, and « replay » internally the last frames in the background so that you cancel the native input lag of some games (which can make them more responsive than games running on real hardware). They could use this option and it’s done. You have a system only working on games like Time Crisis with white frames while shooting, with no white borders nor machine learning model.

    TLDR; if they use AI (=machine learning) as they claim, there will be no constraint like existing alternatives (sensors / white borders), but it will likely be less accurate / responsive. For Time Crisis specifically, it’s possible to come up with a solution without those constraints nowadays, so it’s possible they have no AI at all and use the term for marketing purposes.








  • Probably one of my all-time favorite RPG. It’s a good classic RPG with good graphics and music. The gameplay is good and unique as well, but I remember from my first playthrough back in the days that it took me some time to get used to it. The game is not easy at all (because 2/3 bosses in the game are very hard).

    It’s important not to make a big pause when playing this game. The gameplay starts slow and becomes very fast at some point. It is so unique that, if you stop and play again after a month or so, you will likely have a hard time to become fast enough again (when I played it for the 1st time when I was young, I did this mistake and had to start the game from the beginning).

    I can’t comment about the 2nd game because I never played it.






  • Depends how you see it. TCG is by itself a lootbox game, but with physical cards instead. However, it does not seem that the Pokemon Company wants to turn its TCG game into a digital business, but instead use those apps as promotional products for TCG. Personally, I think it’s a much better model than the one pursued by everyone else. The apps are more a bonus / promotional stuff than a real thing. For this particular app, I won’t be surprised if there is no other way to get packs than waiting for the next day.