
3D Gaussian Splatting - Why Graphics Will Never Be The Same
About this video
A two-minute explainer of 3D Gaussian Splatting, the rendering technique from a 2023 research paper. It outlines why it could change how 3D graphics are made.
Why it appears in the archive
HN uses it as a quick, non-expert primer whenever Gaussian splatting comes up.
AI-generated summary and labels from the source dataset; verify important details against the video. Source & credits.
From the Hacker News discussion
This week I saw a YouTube video which left me impressed regarding Gaussian Splatting. [LINK] I got it recommended because I watched the following video: [VIDEO] Both are worth watching if one didn't know it exists.
Read original comment ↗I am a complete layman in the world of complex computer graphics programming and research, but I have an interest in it as someone who enjoys playing computer games. I really enjoyed this succinct YouTube video on the topic, for those interested in a primer: [VIDEO]
Read original comment ↗This 2-minute video is a great intro to the topic [VIDEO] I think this tech has become "production-ready" recently due to a combination of research progress (the seminal paper was published in 2023 [LINK] ) and improvements to differentiable programming libraries (e.g. PyTorch) and GPU hardware.
Read original comment ↗Youtube recommended this video to me, which concisely explains splatting. Information necessary for trade is there but the trade is left to the viewer. The key drawback that isn't highlighted is that you need a physical space to be a close approximation of what you want to render. So if you want to make a few counter strike maps based off of your workplace (not recommended) then this would be a good technology, but if you want to make an open world on an alien planet you're likely better off with traditional rendering. [VIDEO]
Read original comment ↗> [1] 2 min intro to 3D Gaussian splatting: [VIDEO] I don't know what the hell a "gaussian splat" is and I have to say this video did not help at all.
Read original comment ↗