What had been omitted though was that efficient photorealistic rendering, as well as the visual elements that human perception instantly picks up on such as material(s) translucency, lighting/shadows, and as you've already mentioned animations (and the bigger challenge of facial expressions!) is what everyone's after.
And what we have at the OP is indeed impressive work, which still looks artificial. Contrary to the critique of the comments so far, and outside the graphics research interpretation, this isn't something necessarily negative imo. I like video games that preserve a few elements of non-photorealism.
Sure, you can compare two and tell which one is better but unless it is really bad humans won’t be bothered by it or even explain what’s wrong.
Don't get me wrong, the visual clarity is a great achievement. But if they're gonna spend more effort on making it more convincingly real, that's a better target IMO than reflections and wave patterns.
And the camera is very smooth, which filters out the little balance shifts we all do (even typing something here I notice the subtle changes to vision oscillating in complex patterns which head-bobbing would be a simplified first-order approach to).
I assume it's still very difficult to do all these things with current computing power, and in the case of the camera I'm not sure it will ever be possible for something interactive to feel quite perfect unless you switch to a VR headset and carry your own balance into it.
At least, the fact that this game has familiar human movement tropes that resembles decade old games sounds like a testament to that.
GTA 3/4/5 are in the megalotesticle category (characters moving like wavering boats).
It feels like character movements haven’t changed much in the last 20 years. Which is a shame because the visuals are great, but let down by 2006 style animation.