Train2Game students could end up working on games with Hollywood quality graphics in the next ten years. That’s at least if predictions made by Epic Games founder Tim Sweeny come true.

Epic Games are of course on board for the Train2Game & Epic Game Jam in November.

I really see two major milestones coming up for games in the very long-term future.” Sweeny told IGN UK.

“Number one is achieving movie quality graphics and movie quality pixels on the screen, which mean no flicker in the visuals, no popping artefacts, no bulky character outlines on the screen at all.”

“I see that actually occurring over the next ten years” he said.

And the Epic Games founder believes that computers just need the extra power that will come over the next few years in order to achieve this.

“We just haven’t been able to do it because we don’t have enough terra flops or petta flops of computer power to make it so.”

“I expect over the next ten years we’ll a real revolution in that area as we make up this missing gap between where we are today and everything movies are doing” said Sweeny.

“I expect I’ll be actively programming at the time we’ve achieved full movie-quality graphics because that’s really just a matter of brute force computing power and clever algorithm. We know exactly how to do that” he added.

Train2Game students can get a taste of what games could look like in Epic’s impressive Samaritan tech demo produced using Unreal Engine 3, as seen here on the Train2Game blog.

The Epic games founder suggested that Unreal Engine 4 for next-gen consoles will “probably launch around 2014”

The other major milestone according to Sweeny is creating proper human characters with emotions in games, and this could be improved over the next ten years, although not to the same extent as graphics.

“Simulation of gameplay characters, artificial intelligence, character dialogue and all of these other things aren’t really problems of brute force computing,” said the Epic co-founder.

“They require increasingly sophisticated algorithms and simulation of human intelligence. I have no idea when those problems will be solved. I’m quite sure they won’t be solved in the next ten years.

“They may not even be solved in my lifetime, but those are all problems that require understanding how the human brain works and trying to simulate that with varying degrees of accuracy”

“We’ve seen very, very little progress in these areas over the past few decades so it leaves me very sceptical about our prospects for breakthroughs in the immediate future.” Sweeny concluded.

So Train2Game, what are your thoughts on Sweeny’s comments? Will we see film quality visuals in the next ten years? And do you think games will ever properly crack artificial intelligence?

Leave your comments here on the Train2Game blog, or on the Train2Game forum.

[Source: IGN UK via Develop]